© 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. 12803
    Prev
    Next
    INDEX
    Explanations

    doc tags like @param, @file

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

    The neuron fires on comment annotation markers (the “@” tags) in source‐code documentation.

    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
    obatan
    -1.12
     Dinamarca
    -1.10
     Situationen
    -1.10
    usions
    -1.08
     berbagai
    -1.08
    Leírás
    -1.05
    strategies
    -1.02
    ledad
    -1.02
    Groeten
    -1.00
    hpur
    -0.98
    POSITIVE LOGITS
    </strong>
    1.09
    .
    1.00
     anglès
    0.98
    ?
    0.97
    !
    0.95
    Z
    0.93
    的道
    0.89
    也
    0.88
     also
    0.86
     then
    0.86
    Activations Density 0.001%

    No Known Activations