© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    processes and their results/parameters

    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
    giveness
    -1.41
    bedienung
    -1.39
     Sartre
    -1.37
     overal
    -1.34
    来越
    -1.34
    komsten
    -1.33
    ⌫
    -1.32
    sightly
    -1.30
     royaume
    -1.30
    breviations
    -1.30
    POSITIVE LOGITS
    üdis
    1.54
     at
    1.45
     undertaken
    1.43
    Also
    1.37
     on
    1.34
     it
    1.32
    ..."
    1.31
     anggaran
    1.31
     also
    1.29
     done
    1.29
    Activations Density 0.348%

    No Known Activations