© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 57599
    Prev
    Next
    INDEX
    Explanations

    API documentation titles

    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
     from
    -1.04
     by
    -1.02
     has
    -0.99
     Taking
    -0.93
     as
    -0.93
     encompasses
    -0.90
     with
    -0.90
     their
    -0.87
     because
    -0.87
     not
    -0.86
    POSITIVE LOGITS
     output
    1.20
     OUTPUT
    1.00
     возра
    0.96
     Output
    0.95
     trám
    0.93
    philis
    0.92
     OUT
    0.92
    colle
    0.91
     bút
    0.90
    yesterday
    0.89
    Activations Density 0.003%

    No Known Activations