© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31359
    Prev
    Next
    INDEX
    Explanations

    growth associated

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

    parentheses and other indicators of news sources or citations in articles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     filed
    -0.73
     Thakur
    -0.71
    inserted
    -0.71
     इसमें
    -0.69
     insert
    -0.69
     Walling
    -0.68
     Chapelle
    -0.68
     Jodie
    -0.68
     }}}{
    -0.67
     Superintendent
    -0.67
    POSITIVE LOGITS
    हो
    0.73
    NonUser
    0.73
    ில
    0.72
    Occurred
    0.72
    tilli
    0.70
    omys
    0.69
     Schein
    0.69
    ਹਾ
    0.68
    acchar
    0.68
     suced
    0.68
    Activations Density 0.044%

    No Known Activations