© 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. 108910
    Prev
    Next
    INDEX
    Explanations

    just say

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

    analysis and requirements

    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
    acruz
    0.47
     puissiez
    0.46
     inequities
    0.44
    hap
    0.44
    uzi
    0.44
    inguistic
    0.44
    䡊
    0.43
    phonic
    0.42
     Witherspoon
    0.42
    ometrically
    0.42
    POSITIVE LOGITS
     e
    0.48
     p
    0.46
     dan
    0.45
    OP
    0.45
    자와
    0.44
     comerc
    0.44
     Industrial
    0.44
     compan
    0.43
     leading
    0.43
     și
    0.43
    Activations Density 0.000%

    No Known Activations