© 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. 140068
    Prev
    Next
    INDEX
    Explanations

    still own, Applied Behavior, stages arranged, text within

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

    meta key

    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
    Negative Logits
    ABLES
    0.55
     Inglaterra
    0.53
    ルの
    0.52
    ंबी
    0.51
     axles
    0.50
    .??.??"]
    0.49
    きち
    0.49
     RULES
    0.49
    ரூ
    0.48
     territorios
    0.48
    POSITIVE LOGITS
    ament
    0.52
    otra
    0.50
     laptop
    0.50
    <
    0.50
    “[
    0.49
    _
    0.48
    0.46
    ¼
    0.45
     billboard
    0.45
    oud
    0.45
    Activations Density 0.001%

    No Known Activations