© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77824
    Prev
    Next
    INDEX
    Explanations

    business names and services

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on key industry or service–type nouns (e.g. “Mulch,” “Transmission,” “Roofing,” “Flooring”) that denote a business’s line of work.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    business names in the construction, home services, and trades industries.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    industry and service category nouns used in business names or headings, especially in construction, home improvement, and retail services.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mueble
    -1.09
     menurut
    -0.90
    になったら
    -0.87
    anwalt
    -0.84
    になりますが
    -0.84
     эти
    -0.83
    Plural
    -0.81
    gens
    -0.81
    にします
    -0.81
    ängel
    -0.81
    POSITIVE LOGITS
     &
    1.21
     Supply
    1.19
     Center
    1.19
     LLC
    1.18
     Company
    1.09
     company
    1.05
    CENTER
    1.05
     located
    1.04
    center
    1.03
    works
    1.02
    Activations Density 0.048%

    No Known Activations