© 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. 34-GEMMASCOPE-RES-131K
    7. 63723
    Prev
    Next
    INDEX
    Explanations

    distributed under the MIT license

    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_34/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
    Tä
    -1.04
     playera
    -1.02
    NameExpr
    -1.02
     PUSTAKA
    -1.00
    破解
    -0.99
     visuel
    -0.98
    Ұ
    -0.98
    обзор
    -0.97
     sué
    -0.96
     hadas
    -0.96
    POSITIVE LOGITS
     don
    0.97
     включа
    0.97
     how
    0.97
     those
    0.95
     specialmente
    0.95
    (
    0.94
     bekannte
    0.94
     especially
    0.93
     connection
    0.91
    do
    0.90
    Activations Density 0.001%

    No Known Activations