© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129775
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

    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_22/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
     apprécier
    -1.10
     réserver
    -1.09
     genoux
    -1.02
    ところは
    -1.00
     Palest
    -0.99
     gangen
    -0.99
     rappresenta
    -0.98
    就是
    -0.98
    を行います
    -0.96
     desglose
    -0.96
    POSITIVE LOGITS
     in
    1.27
     when
    1.13
     before
    1.05
    llllll
    1.00
     as
    0.98
     and
    0.98
    bourhood
    0.97
     at
    0.93
    ternut
    0.92
    obox
    0.92
    Activations Density 0.039%

    No Known Activations