© 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. 34-GEMMASCOPE-RES-131K
    7. 33259
    Prev
    Next
    INDEX
    Explanations

    permit persons

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

    The neuron fires on non‐alphanumeric punctuation characters—especially those used in ASCII art or emphasis (e.g. slashes, underscores, pipes, quotes, and similar symbols).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    werfen
    -0.69
     Hush
    -0.69
     modernen
    -0.68
    ቃ
    -0.67
    Hush
    -0.67
    为自己
    -0.67
     Rm
    -0.66
    ulose
    -0.66
    apiKey
    -0.65
    给自己
    -0.65
    POSITIVE LOGITS
    Larry
    0.71
     genotype
    0.69
    Prince
    0.67
    Blake
    0.67
    ecimento
    0.65
     maj
    0.65
    ANCES
    0.65
    pgfmath
    0.65
    Release
    0.64
     Akshay
    0.64
    Activations Density 0.042%

    No Known Activations