© 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. 63087
    Prev
    Next
    INDEX
    Explanations

    Kensington and related locations

    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
    DECREF
    -0.73
    鈽
    -0.73
    klis
    -0.71
    šak
    -0.70
     Fusarium
    -0.69
    মান
    -0.69
    CreatedAt
    -0.68
    条件
    -0.68
    東京
    -0.66
    ˛
    -0.66
    POSITIVE LOGITS
    wag
    0.73
    masuk
    0.71
     между
    0.71
     kri
    0.70
     Palace
    0.69
     FCC
    0.69
    mime
    0.68
    ѵ
    0.68
    SYSTEM
    0.68
    ssing
    0.67
    Activations Density 0.058%

    No Known Activations