© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138300
    Prev
    Next
    INDEX
    Explanations

    historical pages, auto bypass, judges court

    np_acts-logits-general · gemini-2.5-flash-lite

    Domain adaptation, younger patients, rows, brand, avoiding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hawke
    0.43
     Colón
    0.42
     Beh
    0.42
     Quin
    0.42
     Snowdon
    0.42
     Quinn
    0.41
     与
    0.41
     bagaimana
    0.40
     Bike
    0.40
     individuality
    0.40
    POSITIVE LOGITS
    ឲ
    0.46
     hostile
    0.44
     unfriendly
    0.42
    了大
    0.40
    тили
    0.40
    ogiri
    0.39
     заяв
    0.38
     шла
    0.38
     категори
    0.38
    icolored
    0.38
    Activations Density 0.001%

    No Known Activations