© 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. 144120
    Prev
    Next
    INDEX
    Explanations

    legacy and comments

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

    Notebook, bottom, slab

    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
     tấm
    0.49
     longstanding
    0.46
     بلا
    0.46
     галакти
    0.45
     و
    0.45
     tissu
    0.44
     ткань
    0.44
    公务
    0.43
    iscid
    0.42
     vigente
    0.42
    POSITIVE LOGITS
    繼
    0.44
    ಯು
    0.44
    スパ
    0.43
    mother
    0.42
    jeu
    0.42
    OTT
    0.42
    جين
    0.40
     juc
    0.40
    HOP
    0.40
     Hopl
    0.40
    Activations Density 0.001%

    No Known Activations