© 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. 252448
    Prev
    Next
    INDEX
    Explanations

    dates and exams

    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
    แค
    0.50
     क्वाड्र
    0.50
     உற்ப
    0.48
    ﻌ
    0.48
     නිෂ්පා
    0.48
     иң
    0.46
     ఉత్ప
    0.46
     ị
    0.46
    Miscellaneous
    0.46
    财
    0.46
    POSITIVE LOGITS
    ように
    0.49
    ри
    0.47
    Setpoint
    0.47
    exist
    0.46
    <sub>
    0.45
    roje
    0.45
     divinity
    0.44
     zodat
    0.44
    ваме
    0.44
    reiben
    0.43
    Activations Density 0.002%

    No Known Activations