© 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. 10-GEMMASCOPE-RES-131K
    7. 22430
    Prev
    Next
    INDEX
    Explanations

    Shu, Garry, Jasper, queryString, TEntity, lx

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

    The neuron activates on capitalized proper names and named-entity tokens (people, organizations, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </em>
    -2.84
    The
    -2.78
    韞
    -2.63
    }{
    -2.59
     motivates
    -2.53
    providedIn
    -2.50
     préférable
    -2.45
    ～～
    -2.44
    <em>
    -2.38
     worrying
    -2.36
    POSITIVE LOGITS
    ’
    2.89
    鯪
    2.81
    s
    2.75
    鵟
    2.70
    戗
    2.70
    during
    2.64
    羕
    2.52
     CHANGE
    2.34
     Eropa
    2.33
     For
    2.27
    Activations Density 0.045%

    No Known Activations