© 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. 8512
    Prev
    Next
    INDEX
    Explanations

    starts of sections or phrases

    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
     or
    -2.00
     and
    -1.95
     Using
    -1.73
     use
    -1.66
     in
    -1.58
     expansive
    -1.50
     old
    -1.48
     new
    -1.47
     For
    -1.46
    :✨
    -1.45
    POSITIVE LOGITS
    probably
    1.66
    棡
    1.63
     atractivos
    1.58
    unfortunately
    1.52
    Dette
    1.51
     probablement
    1.49
    despite
    1.48
     essentiellement
    1.48
     hermosos
    1.47
    屢
    1.47
    Activations Density 0.000%

    No Known Activations