© 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. 10-GEMMASCOPE-RES-131K
    7. 72600
    Prev
    Next
    INDEX
    Explanations

    context.current

    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_10/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
    various
    -1.38
    first
    -1.27
    fl
    -1.13
     eisen
    -1.13
     sieht
    -1.09
     molti
    -1.08
    m
    -1.08
    {}\
    -1.07
    了很多
    -1.07
    different
    -1.07
    POSITIVE LOGITS
    thiết
    1.50
    identifikasi
    1.48
    bảng
    1.37
    collana
    1.36
     time
    1.34
     čase
    1.34
    阵容
    1.27
    nhà
    1.27
    dungen
    1.27
    lampada
    1.24
    Activations Density 0.056%

    No Known Activations