© 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. 44332
    Prev
    Next
    INDEX
    Explanations

    database data types

    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
     their
    -1.96
     there
    -1.91
     it
    -1.84
     many
    -1.77
     a
    -1.63
    ziem
    -1.57
     being
    -1.57
     some
    -1.56
     your
    -1.47
     several
    -1.46
    POSITIVE LOGITS
    Those
    1.84
     těch
    1.69
     verhind
    1.67
    こともあります
    1.67
     моих
    1.66
     besonder
    1.62
     эти
    1.53
     этих
    1.53
     toujours
    1.52
     páns
    1.48
    Activations Density 0.030%

    No Known Activations