© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7329
    Prev
    Next
    INDEX
    Explanations

    League, baseball, Inc., vista

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    RK
    -0.65
    SCH
    -0.63
    Click
    -0.63
    Cel
    -0.63
     necessities
    -0.61
     Farn
    -0.60
    有所
    -0.60
    taba
    -0.59
     conséquent
    -0.59
     RK
    -0.59
    POSITIVE LOGITS
    CAPTCHA
    0.69
     vinos
    0.66
    indent
    0.65
    རྒྱ
    0.65
    elm
    0.63
    Culti
    0.62
    tole
    0.62
    Fetched
    0.62
    🛼
    0.61
     fuelled
    0.60
    Activations Density 0.067%

    No Known Activations