© 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. 36351
    Prev
    Next
    INDEX
    Explanations

    command-line code and scripts

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

    This neuron flags programming-language identifiers and keywords (e.g. function names, type names, and other code tokens).

    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
    ")){
    -0.87
    ранже
    -0.84
     trouvait
    -0.84
    ');?>
    -0.83
     déroule
    -0.83
    ')).
    -0.83
    \\
    -0.83
    irlo
    -0.82
    konzept
    -0.81
     総合
    -0.81
    POSITIVE LOGITS
    üme
    0.98
    咪
    0.87
     tentunya
    0.86
    現貨
    0.83
    quando
    0.83
    僰
    0.82
    雖然
    0.81
     impacto
    0.79
     deple
    0.79
    עות
    0.78
    Activations Density 0.004%

    No Known Activations