© 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. 73897
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY AUTOINCREMENT

    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
     have
    -2.08
     in
    -1.84
     with
    -1.72
     has
    -1.72
     on
    -1.69
     generally
    -1.68
     seems
    -1.66
     as
    -1.65
     With
    -1.64
     a
    -1.63
    POSITIVE LOGITS
    ,
    1.93
    </em>
    1.70
     tą
    1.59
    崀
    1.58
    rovnik
    1.56
     plek
    1.55
     actie
    1.49
    nargs
    1.49
     taką
    1.48
     takimi
    1.46
    Activations Density 0.004%

    No Known Activations