© 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. 22-GEMMASCOPE-RES-131K
    7. 128958
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on prominent multi‐syllable nouns referring to technical, medical, or scientific concepts.

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

    technology and health concepts

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

    technical devices and technologies like computers, phones, browsers, and medical equipment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    D
    -1.26
    B
    -1.16
    b
    -1.15
    K
    -1.14
    p
    -1.12
    Dan
    -1.10
    q
    -1.10
    Ben
    -1.09
    ED
    -1.08
    w
    -1.08
    POSITIVE LOGITS
     that
    1.58
     aparato
    1.32
     with
    1.18
     Frases
    1.12
    УДК
    1.08
    Sumber
    1.06
     personnalité
    1.05
     blusa
    1.02
     using
    1.02
     through
    1.02
    Activations Density 0.213%

    No Known Activations