© 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. 41918
    Prev
    Next
    INDEX
    Explanations

    the static

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

    analyzing data, instructions, or content

    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
     自分
    0.48
     Wirtschafts
    0.48
     ấy
    0.47
     awakened
    0.45
     ダウン
    0.45
     または
    0.45
     岩
    0.44
     ウォ
    0.44
     Recurring
    0.44
     という
    0.44
    POSITIVE LOGITS
    ק
    0.48
     considerados
    0.47
    ढ़ाई
    0.46
    私募基金
    0.44
    ہ
    0.44
    TWO
    0.44
    dean
    0.44
     habeas
    0.43
    фе
    0.43
    Sham
    0.43
    Activations Density 0.000%

    No Known Activations