© 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. 70040
    Prev
    Next
    INDEX
    Explanations

    smash and grab accounts

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

    explanation types of breaks

    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
    न्थ
    0.56
    逞
    0.54
    다면
    0.52
    ाल
    0.50
    ంటు
    0.49
    Ი
    0.49
    भर
    0.48
    禇
    0.47
    दा
    0.47
    ੁੰ
    0.46
    POSITIVE LOGITS
    cc
    0.52
    oug
    0.49
     exclaimed
    0.48
    wen
    0.48
    aken
    0.48
    oram
    0.48
     націона
    0.48
    vspace
    0.47
    enz
    0.47
    bb
    0.46
    Activations Density 0.001%

    No Known Activations