© 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. 206076
    Prev
    Next
    INDEX
    Explanations

    New York City

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

    technical instructions and code

    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
     dicht
    0.53
     procédé
    0.50
    }(\
    0.49
     decomp
    0.48
     chiam
    0.46
     levou
    0.45
     чисто
    0.45
     сфор
    0.45
    }}$,
    0.44
    чів
    0.44
    POSITIVE LOGITS
    ходим
    0.48
    York
    0.46
     Breeders
    0.44
    beet
    0.44
    नेश
    0.44
    Jenkins
    0.44
    accounts
    0.43
    ارهای
    0.43
     Bulldogs
    0.43
    yen
    0.43
    Activations Density 0.000%

    No Known Activations