© 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. 19871
    Prev
    Next
    INDEX
    Explanations

    execute() calls and examples

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

    code formatting and symbols

    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
    ე
    0.42
    ất
    0.42
    ֶ
    0.41
    禄
    0.40
    è
    0.39
    އް
    0.39
    é
    0.39
    éa
    0.38
     behest
    0.38
     sein
    0.38
    POSITIVE LOGITS
    那些
    0.44
     scrollBody
    0.42
     그렇지
    0.41
     রাখার
    0.40
    實際
    0.40
     করিয়াছিল
    0.39
    他們
    0.38
     পাকিস্তানীদের
    0.38
     করিয়৷
    0.38
     উপরের
    0.38
    Activations Density 0.001%

    No Known Activations