© 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. 149839
    Prev
    Next
    INDEX
    Explanations

    final book

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

    technical terms and non-conventional descriptions

    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
    <0xD3>
    0.53
    ğından
    0.53
     மெ
    0.50
     మె
    0.47
    грамма
    0.47
     Adin
    0.47
    发起
    0.47
     ס
    0.46
    ələ
    0.46
    ses
    0.45
    POSITIVE LOGITS
    阊
    0.53
    Ꮡ
    0.46
    امة
    0.45
     Prolong
    0.44
     рэгістрацыі
    0.44
     stvar
    0.43
    DMSO
    0.43
     thấp
    0.43
     pcMove
    0.42
     coerced
    0.42
    Activations Density 0.001%

    No Known Activations