© 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. 169293
    Prev
    Next
    INDEX
    Explanations

    movement and time duration

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

    will not encryption

    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
     आये
    0.54
    ui
    0.52
    <unused61>
    0.52
     brackets
    0.51
     UI
    0.50
     db
    0.49
     Cd
    0.48
     अहमदाबाद
    0.48
     );
    0.48
     Archived
    0.48
    POSITIVE LOGITS
    ل
    0.51
    طان
    0.48
    ตัน
    0.48
    LongNumber
    0.47
    كاته
    0.47
    ნ
    0.46
    Tens
    0.46
    レッ
    0.46
    Ellipse
    0.46
    نګ
    0.45
    Activations Density 0.000%

    No Known Activations