© 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. 22350
    Prev
    Next
    INDEX
    Explanations

    Superman or KM entities

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

    The neuron fires on alphanumeric codes or identifiers—strings of uppercase letters immediately followed by digits (e.g. “SuppressLint 220,” “KM 144,” “KM 136,” 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
    .,
    -2.50
    atasaray
    -2.31
    jenigen
    -2.17
     volete
    -2.16
     lidé
    -2.13
    ;
    -2.09
     in
    -2.09
     飲
    -2.06
     to
    -2.06
     nová
    -2.03
    POSITIVE LOGITS
    or
    3.06
    at
    2.50
    they
    2.36
    红色的
    2.33
    ことです
    2.28
    you
    2.23
    x
    2.20
    ۠
    2.16
    before
    2.14
     essayer
    2.14
    Activations Density 0.004%

    No Known Activations