© 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. 144669
    Prev
    Next
    INDEX
    Explanations

    laced nectar; these funding

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

    file renaming tags

    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
     اقصیٰ
    0.49
    ANGLE
    0.46
     อีก
    0.44
     निकालेंगे
    0.44
    虢
    0.43
     জানিতে
    0.43
    രിക്ക
    0.41
    Nam
    0.41
     chcete
    0.41
    wish
    0.40
    POSITIVE LOGITS
     о
    0.49
    о
    0.48
    ensely
    0.47
    ネットワーク
    0.46
     ведь
    0.46
     смерть
    0.46
     ओ
    0.45
     उर्
    0.44
     growing
    0.44
    ка
    0.43
    Activations Density 0.000%

    No Known Activations