© 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. 22-GEMMASCOPE-RES-131K
    7. 93277
    Prev
    Next
    INDEX
    Explanations

    code arguments

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

    The neuron fires on identifiers used as function parameters (e.g. variable names in argument lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     from
    -1.50
     without
    -1.45
     while
    -1.34
     has
    -1.30
     allows
    -1.24
     before
    -1.20
     in
    -1.20
     because
    -1.17
     or
    -1.16
     with
    -1.15
    POSITIVE LOGITS
     élar
    1.17
    出道
    1.16
    Anche
    1.15
     famed
    1.06
     potrebbe
    1.05
     REALLY
    1.04
     novamente
    1.03
     dasselbe
    1.00
     dénon
    0.99
    being
    0.98
    Activations Density 0.003%

    No Known Activations