© 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. 56785
    Prev
    Next
    INDEX
    Explanations

    phrases like "objected to", "that point", "party laws"

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

    rain/fall

    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
     geniuses
    0.43
    ганда
    0.42
    webElement
    0.42
     carbohydrates
    0.40
    ReactNativeHost
    0.40
    参考に
    0.40
    (|\
    0.40
    TeV
    0.40
     campaigners
    0.40
    enseignement
    0.39
    POSITIVE LOGITS
     și
    0.45
     Lorsque
    0.43
    Restriction
    0.41
     चाँ
    0.41
     dikenal
    0.41
    ର୍
    0.41
    餘
    0.40
     menyebabkan
    0.40
     formas
    0.39
    ىرى
    0.39
    Activations Density 0.000%

    No Known Activations