© 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. 247130
    Prev
    Next
    INDEX
    Explanations

    free templates and documents

    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
     ไข
    0.47
    洨
    0.47
    केशन
    0.46
     น
    0.45
    生理
    0.45
     ส
    0.45
     ซ
    0.45
     วิ
    0.45
    砸
    0.45
     ৫ম
    0.44
    POSITIVE LOGITS
    ہ
    0.50
    ston
    0.49
    count
    0.48
    chino
    0.47
    alya
    0.46
    write
    0.46
     sweatshirt
    0.46
     believer
    0.46
     verbal
    0.45
    꾼
    0.45
    Activations Density 0.001%

    No Known Activations