© 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. 40047
    Prev
    Next
    INDEX
    Explanations

    actions done easily

    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
    possibly
    -1.78
    eventually
    -1.63
     alimente
    -1.50
    ܆
    -1.48
    </strong>
    -1.45
     católica
    -1.44
     eventually
    -1.40
     then
    -1.40
     definitiv
    -1.40
    perhaps
    -1.38
    POSITIVE LOGITS
     will
    2.34
     of
    1.54
    ējās
    1.48
     pomocí
    1.41
     helps
    1.41
     would
    1.36
     easy
    1.30
    umą
    1.29
     easily
    1.28
     aukš
    1.27
    Activations Density 0.023%

    No Known Activations