© 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. 100094
    Prev
    Next
    INDEX
    Explanations

    death, inquiries, government, intolerant, peril

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

    Justinian, Ordering Service, Data Center Revenue

    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
    ignac
    0.58
    ac
    0.57
    fim
    0.54
    birthday
    0.54
    w
    0.54
    sp
    0.54
    mailing
    0.53
    pres
    0.52
    viv
    0.52
    ema
    0.52
    POSITIVE LOGITS
     ప్రయత్
    0.55
    决心
    0.49
     größeren
    0.48
    యత్
    0.47
     약간
    0.46
     Determines
    0.46
     dataType
    0.45
    成了
    0.45
     것은
    0.45
    𝘺
    0.44
    Activations Density 0.000%

    No Known Activations