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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 54085
    Prev
    Next
    INDEX
    Explanations

    structure/component names

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

    The neuron fires on longer, domain-specific “content” words—especially multi-syllable technical or scientific terms.

    oai_token-act-pair · o4-miniTriggered 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
    forRoot
    -0.82
    拌
    -0.82
    montre
    -0.77
    ittà
    -0.75
     déficit
    -0.74
     الفيلم
    -0.74
    ONOM
    -0.73
    Taco
    -0.73
     inau
    -0.73
    愴
    -0.73
    POSITIVE LOGITS
     item
    1.32
     category
    1.19
     module
    1.16
     entity
    1.08
     option
    1.05
     project
    1.02
     section
    1.01
     estancia
    0.99
     article
    0.96
     modality
    0.96
    Activations Density 0.195%

    No Known Activations