© 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. 92709
    Prev
    Next
    INDEX
    Explanations

    copyright and license headers

    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
    ható
    -0.77
    Dung
    -0.72
    claim
    -0.72
    nce
    -0.72
    naden
    -0.70
    ABLO
    -0.70
     樹
    -0.69
    abello
    -0.68
    Toy
    -0.67
    ękuję
    -0.66
    POSITIVE LOGITS
    牲
    0.76
    係
    0.66
    cangan
    0.66
    дивиду
    0.66
     deliver
    0.65
    推送
    0.63
    โล
    0.63
     Gifford
    0.63
     Position
    0.63
     Most
    0.63
    Activations Density 0.045%

    No Known Activations