© 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. 14835
    Prev
    Next
    INDEX
    Explanations

    code file headers

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

    The neuron primarily detects numeric literals (numbers, including integers and floating‐point constants) in code.

    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
     and
    -1.63
     conversely
    -1.53
     currently
    -1.53
    recent
    -1.38
     более
    -1.32
     localizada
    -1.32
     a
    -1.30
     in
    -1.29
     nombreuses
    -1.24
     utilisons
    -1.23
    POSITIVE LOGITS
     forskjellige
    1.35
    錒
    1.31
    ISTICAL
    1.31
     لا
    1.30
    kunjung
    1.29
    ATIVE
    1.27
     luf
    1.26
     Nieuwe
    1.26
     ändå
    1.23
    udnio
    1.23
    Activations Density 0.059%

    No Known Activations