© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10479
    Prev
    Next
    INDEX
    Explanations

    hum permeating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ٭
    2.50
     lying
    2.49
    ・・・・
    2.37
    imple
    2.37
     Име
    2.36
     खाद्य
    2.36
     فیصل
    2.31
     لوی
    2.30
     الو
    2.29
    ｅ
    2.28
    POSITIVE LOGITS
    quy
    2.66
     kèo
    2.60
     bóng
    2.59
     tử
    2.58
    ड़क
    2.55
    ên
    2.51
    Ớ
    2.48
    𝓹
    2.48
     AppleWebKit
    2.41
    Filler
    2.40
    Activations Density 0.007%

    No Known Activations