© 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. 185000
    Prev
    Next
    INDEX
    Explanations

    production operation

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

    specific explanations

    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
     Viitattu
    0.53
    豳
    0.51
     Played
    0.50
     नियुक्त
    0.48
     Уен
    0.47
     Biraz
    0.47
    滃
    0.46
     прият
    0.46
    钗
    0.46
    oacute
    0.46
    POSITIVE LOGITS
     progressively
    0.45
    کر
    0.44
     casing
    0.44
     journalistic
    0.43
     commentaries
    0.43
     indentation
    0.42
    ivariable
    0.42
     subsequ
    0.42
     classe
    0.41
    ritic
    0.41
    Activations Density 0.001%

    No Known Activations