© 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. 74434
    Prev
    Next
    INDEX
    Explanations

    come, split, or what

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

    standing on, taking little, torque function, lab coat

    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
     Karth
    0.52
    C
    0.47
    maktadır
    0.46
     där
    0.46
     où
    0.45
     Aldi
    0.44
     donde
    0.43
    ،
    0.42
     chức
    0.41
    SequentialGroup
    0.41
    POSITIVE LOGITS
     μιας
    0.43
     zariaden
    0.43
     軍
    0.43
    鈾
    0.43
     تجه
    0.42
     緊急
    0.42
     вже
    0.42
     бага
    0.42
    鐵
    0.42
     paciente
    0.41
    Activations Density 0.002%

    No Known Activations