© 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. 144088
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

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

    dough, feathered, never grows, sanity

    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
     MARKET
    0.48
    OD
    0.46
    Easy
    0.45
    '
    0.45
    就
    0.44
     Market
    0.44
     easier
    0.44
    market
    0.44
    SIE
    0.44
     HIS
    0.44
    POSITIVE LOGITS
     ജീവിത
    0.51
    وين
    0.51
     نوفمبر
    0.50
    revalidator
    0.49
    ♉
    0.48
    ويل
    0.48
    <unused666>
    0.48
    ्योर
    0.47
    кета
    0.46
     аў
    0.46
    Activations Density 0.001%

    No Known Activations