© 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. 208164
    Prev
    Next
    INDEX
    Explanations

    text within quotation marks

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

    attributes and resources

    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
     沖縄
    0.46
    ’
    0.45
     ضد
    0.45
     бюро
    0.45
     ঢুক
    0.44
     অব্যাহত
    0.44
    costcenter
    0.44
     urgently
    0.44
    ײ
    0.44
    nın
    0.43
    POSITIVE LOGITS
     manipulated
    0.52
     manipulate
    0.47
     heave
    0.47
     tou
    0.44
     gott
    0.44
     idk
    0.42
    osu
    0.41
    el
    0.41
     leistungs
    0.41
     pares
    0.40
    Activations Density 0.002%

    No Known Activations