© 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. 178171
    Prev
    Next
    INDEX
    Explanations

    Kickstarter campaign

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

    follows definition or explanation

    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
     важное
    0.50
     मानदंड
    0.46
    Ngày
    0.46
     सराह
    0.45
     важ
    0.44
    惋
    0.44
     बेशक
    0.44
    Vide
    0.43
     કેટલાક
    0.43
    鍥
    0.43
    POSITIVE LOGITS
     prelude
    0.54
     self
    0.54
     themes
    0.54
     decorative
    0.54
     direct
    0.53
     skins
    0.53
     utterances
    0.53
     deprec
    0.53
     mousse
    0.53
     delimiters
    0.53
    Activations Density 0.001%

    No Known Activations