© 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. 38299
    Prev
    Next
    INDEX
    Explanations

    gene, detailed, per, Q, PED

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

    opening curly braces and conditionals in programming/markup code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on JavaScript anonymous‐function constructs, i.e. the “function()” keyword plus its call parentheses.

    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
    Untuk
    -1.11
    нії
    -1.07
     搞笑
    -1.04
    ఈ
    -0.99
     cadáver
    -0.99
     blusas
    -0.99
    孔子
    -0.93
     volantes
    -0.92
    сение
    -0.92
    Jika
    -0.91
    POSITIVE LOGITS
     nor
    1.22
    ho
    1.04
    k
    1.01
    ch
    0.98
    fa
    0.98
    ra
    0.96
    t
    0.96
    den
    0.96
    es
    0.95
    co
    0.95
    Activations Density 0.000%

    No Known Activations