© 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. 53998
    Prev
    Next
    INDEX
    Explanations

    television series, district of, states that, system clock

    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
    BaseResponse
    -0.82
     trucks
    -0.70
    createDate
    -0.69
     captivity
    -0.69
     lucu
    -0.69
     '_
    -0.65
    Bson
    -0.65
    SetState
    -0.63
     _
    -0.63
    Coast
    -0.63
    POSITIVE LOGITS
     począ
    0.72
    Sci
    0.72
     लाग
    0.72
     výkon
    0.70
     praw
    0.70
    ùng
    0.68
    CP
    0.67
     Hirst
    0.66
     CP
    0.65
     flavon
    0.65
    Activations Density 0.054%

    No Known Activations