© 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. 33652
    Prev
    Next
    INDEX
    Explanations

    path: followed by :, ., or text

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

    The neuron fires on long, multi‐syllable chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to numbers and numeric formatting, such as digits and punctuation that mark dates, times, ratios, and other numeric values.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    colons in structured data formats like code, configuration files, timestamps, and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     life
    -0.69
     Attack
    -0.68
     attacking
    -0.67
    upply
    -0.66
     trụ
    -0.66
     Buchstaben
    -0.65
    life
    -0.64
     powierzchni
    -0.64
    ff
    -0.64
     mocy
    -0.63
    POSITIVE LOGITS
    bustion
    0.73
    ceton
    0.71
    ghen
    0.69
    uncia
    0.69
     CARD
    0.67
     Domingo
    0.67
     มัน
    0.66
     skier
    0.66
    ローチ
    0.65
    unnamed
    0.65
    Activations Density 0.054%

    No Known Activations