© 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. 93274
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    The neuron fires on variable names used as function parameters (i.e. argument identifiers in definitions or callbacks).

    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
    віть
    -0.81
     použ
    -0.80
     paren
    -0.77
     tộc
    -0.76
    agra
    -0.75
    umme
    -0.75
     veckan
    -0.75
    ility
    -0.75
    そんな
    -0.74
     havoc
    -0.73
    POSITIVE LOGITS
    صورة
    0.90
    чая
    0.85
     lawfully
    0.84
     Jennings
    0.82
     golf
    0.82
     páns
    0.82
     chair
    0.81
    ității
    0.80
     a
    0.79
     YOURSELF
    0.77
    Activations Density 0.041%

    No Known Activations