© 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. 30169
    Prev
    Next
    INDEX
    Explanations

    factorise, factor out, when using, index starts, this game, click here, sort by, error by, call:

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

    simplifying and factoring equations

    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
    Negative Logits
     einer
    0.44
    Gil
    0.41
     a
    0.39
     an
    0.39
    Le
    0.38
     German
    0.38
    某个
    0.37
    <strong>
    0.37
     isang
    0.36
    A
    0.36
    POSITIVE LOGITS
    imgInit
    0.45
     優
    0.45
     GoObject
    0.43
     為
    0.42
    πως
    0.41
    urètre
    0.40
     үшін
    0.40
    andı
    0.40
     semelh
    0.40
    бр
    0.40
    Activations Density 0.001%

    No Known Activations