© 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. 22-GEMMASCOPE-RES-131K
    7. 25598
    Prev
    Next
    INDEX
    Explanations

    compound nouns identifying subjects

    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
     delectable
    -1.02
    啐
    -1.02
     THESIS
    -0.96
     Perſ
    -0.96
     Auschwitz
    -0.96
     любы
    -0.94
    ленного
    -0.93
     Conſ
    -0.93
    ఱ
    -0.92
    秾
    -0.91
    POSITIVE LOGITS
     all
    1.05
     first
    1.01
     will
    1.01
     According
    1.01
     then
    1.00
     keeps
    0.99
     December
    0.99
     vēl
    0.97
    ：……
    0.96
     after
    0.96
    Activations Density 0.000%

    No Known Activations