© 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. 34304
    Prev
    Next
    INDEX
    Explanations

    office, sessions OR dance, yard, at chapel, HR tools, text, BIG bar

    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
     Patrick
    -0.91
    pova
    -0.78
     dozens
    -0.78
     Certified
    -0.77
    lrrr
    -0.75
    Yen
    -0.75
     ступен
    -0.75
    omiast
    -0.75
     amidst
    -0.74
    優勝
    -0.73
    POSITIVE LOGITS
    Residents
    0.90
    ﺔ
    0.89
    ภายใน
    0.88
     внутріш
    0.88
    atzung
    0.88
    interno
    0.85
    WARD
    0.85
    віть
    0.84
     Reſ
    0.84
     unserer
    0.83
    Activations Density 0.226%

    No Known Activations