© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39257
    Prev
    Next
    INDEX
    Explanations

    substituting values or parameters

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

    The neuron detects occurrences of words or word stems related to “substitute” (e.g. substitute, substituting, substitution).

    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
    香味
    -1.06
     contaminación
    -1.02
    丶
    -0.99
     attendant
    -0.98
     انتخاب
    -0.97
    一八
    -0.96
    未使用
    -0.96
    挽回
    -0.95
    PHPExcel
    -0.95
     lorsqu
    -0.92
    POSITIVE LOGITS
     into
    1.63
     the
    1.39
     our
    1.26
     to
    1.09
     in
    1.00
    وگرافی
    0.96
    ^+
    0.95
     about
    0.95
     now
    0.95
     strana
    0.93
    Activations Density 0.004%

    No Known Activations