© 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. 58605
    Prev
    Next
    INDEX
    Explanations

    quoted text indicators

    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
     in
    -1.28
     from
    -1.23
     so
    -1.10
     takes
    -1.09
     with
    -1.09
     on
    -1.06
     making
    -1.06
     less
    -1.05
     had
    -1.04
     just
    -1.03
    POSITIVE LOGITS
    >
    1.17
     apporter
    1.04
    already
    0.99
     résister
    0.97
     récol
    0.96
     gurus
    0.96
     différents
    0.94
     havet
    0.94
     spektak
    0.93
     couvrir
    0.93
    Activations Density 0.032%

    No Known Activations