© 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. 63183
    Prev
    Next
    INDEX
    Explanations

    long duration

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

    control and exploitation

    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
    ठभे
    0.44
    prüng
    0.40
    ྃ
    0.39
    遇到了
    0.39
    ய்
    0.38
    urre
    0.38
     পের
    0.38
    ณิต
    0.37
    ilibus
    0.37
    selectable
    0.37
    POSITIVE LOGITS
     lasted
    0.50
     Effekt
    0.47
    吊
    0.45
    ్రీన్
    0.44
     gaps
    0.43
     duration
    0.42
     maw
    0.42
    少ない
    0.42
    ओसी
    0.42
    長時間
    0.41
    Activations Density 0.000%

    No Known Activations