© 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. 196904
    Prev
    Next
    INDEX
    Explanations

    suppliers & exporters

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

    suicide & crisis lifeline

    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
    ก
    0.54
    _
    0.53
    ﯿ
    0.53
    ంగ్
    0.52
    레
    0.49
    ಬ
    0.48
    馄
    0.47
    ด
    0.47
    вая
    0.47
    Ꮴ
    0.46
    POSITIVE LOGITS
    amp
    0.54
    افظ
    0.51
    কালের
    0.51
    uci
    0.50
    otts
    0.50
    বিভিন্ন
    0.49
    sleeping
    0.49
    economy
    0.48
    অর্থ
    0.48
    ingly
    0.47
    Activations Density 0.007%

    No Known Activations