© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85162
    Prev
    Next
    INDEX
    Explanations

    giving options or reasons

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

    phase formation or online learning

    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
    毉
    0.48
     ลักษณะ
    0.48
     கொலை
    0.46
    Physical
    0.44
    Treatment
    0.44
    ลักษณะ
    0.43
     ﺍﻟ
    0.42
    ্বরের
    0.42
    ()!=
    0.42
    Residential
    0.42
    POSITIVE LOGITS
    atau
    0.50
    述
    0.50
    ik
    0.50
    ited
    0.49
    eng
    0.47
    op
    0.46
    oplus
    0.46
    elson
    0.45
    us
    0.45
    on
    0.45
    Activations Density 0.000%

    No Known Activations