© 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. 90820
    Prev
    Next
    INDEX
    Explanations

    number of

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

    scratched sample

    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
     расши
    0.44
    గిన
    0.43
    AUS
    0.43
     enjoying
    0.42
     menikmati
    0.41
     terapeut
    0.41
    lcii
    0.40
    脍
    0.39
     titular
    0.39
    Addition
    0.39
    POSITIVE LOGITS
    vay
    0.46
    StatusOK
    0.46
    出來
    0.45
     عمران
    0.43
     Qian
    0.43
     ప్రయత్
    0.43
     unseen
    0.43
    ائل
    0.42
    寫
    0.42
     projectId
    0.42
    Activations Density 0.000%

    No Known Activations