© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    find it

    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
     for
    -2.61
     only
    -2.38
     at
    -2.38
     ostensibly
    -2.34
     as
    -2.34
     on
    -2.34
     first
    -2.27
     even
    -2.25
     after
    -2.25
     because
    -2.23
    POSITIVE LOGITS
     Dinas
    2.31
    鵙
    2.16
    several
    2.16
     geene
    2.11
     joyous
    2.11
    during
    2.11
    えっ
    2.09
    commonly
    2.08
    すっ
    2.06
     ludicrous
    2.05
    Activations Density 0.259%

    No Known Activations