© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2175
    Prev
    Next
    INDEX
    Explanations

    do not use prior knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     به‌عنوان
    0.62
    <unused1341>
    0.57
    正如
    0.54
     =&
    0.52
     হওয়
    0.52
    gmzy
    0.52
    <unused1247>
    0.51
    ⁤
    0.51
    <unused1200>
    0.51
    壴
    0.50
    POSITIVE LOGITS
    ריך
    0.68
     ماں
    0.65
    ่าย
    0.64
     się
    0.63
     Holman
    0.62
    stylesheet
    0.61
     допомогою
    0.59
     Ferien
    0.59
    ఎఫ్
    0.59
    adee
    0.59
    Activations Density 0.825%

    No Known Activations