© 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. 237772
    Prev
    Next
    INDEX
    Explanations

    parent, guide, services

    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
    銥
    0.46
    ពីរ
    0.46
    係
    0.46
    篇
    0.45
    則
    0.44
    千年
    0.43
     tempting
    0.42
     mitigated
    0.42
     pendent
    0.42
    եր
    0.42
    POSITIVE LOGITS
     E
    0.52
     T
    0.52
     או
    0.51
     *
    0.50
     Scientology
    0.48
    lios
    0.47
    ্রো
    0.47
     ব্রিটেন
    0.47
     NE
    0.46
     মায়
    0.46
    Activations Density 0.001%

    No Known Activations