© 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. 26579
    Prev
    Next
    INDEX
    Explanations

    name and title context

    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
     those
    -0.82
     when
    -0.81
    Sheila
    -0.78
     pelagic
    -0.77
    お願いします
    -0.76
     products
    -0.75
    お母
    -0.73
     Bühnen
    -0.71
    caden
    -0.71
    廚房
    -0.70
    POSITIVE LOGITS
     captioned
    1.18
     titled
    1.12
     عنوان
    1.02
    labeled
    0.96
    occupied
    0.95
    称为
    0.93
    ylabel
    0.93
     labeled
    0.93
     title
    0.92
    曰
    0.92
    Activations Density 0.041%

    No Known Activations