© 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. 122810
    Prev
    Next
    INDEX
    Explanations

    advanced calculators, Catherine

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

    credit card, zip, roommate

    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
     ønsk
    0.47
    屼
    0.46
     кар
    0.46
     sí
    0.46
     rés
    0.44
     hran
    0.44
     diem
    0.44
     nach
    0.43
     қар
    0.42
    кар
    0.42
    POSITIVE LOGITS
    نظر
    0.50
    😚
    0.47
    ເຮ
    0.46
    approche
    0.46
    ैटिन
    0.46
    یره
    0.45
    роз
    0.45
    тр
    0.44
    parametri
    0.44
    ამო
    0.44
    Activations Density 0.000%

    No Known Activations