© 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. 112859
    Prev
    Next
    INDEX
    Explanations

    choosing to use hours

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

    specific objects or actions

    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
     Weinberg
    0.51
    他們的
    0.46
     koul
    0.46
    際の
    0.46
    ים
    0.46
    钀
    0.45
    儕
    0.44
    मधील
    0.44
     কিরূপে
    0.44
    ﮯ
    0.44
    POSITIVE LOGITS
     curtail
    0.44
    )=>{
    0.43
     rethinking
    0.43
    ​.
    0.42
    ຈ
    0.42
     remand
    0.42
    ใ
    0.42
     smarter
    0.41
     cardboard
    0.41
     foci
    0.41
    Activations Density 0.000%

    No Known Activations