© 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. 2190
    Prev
    Next
    INDEX
    Explanations

    numeric/symbolic code and words

    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
    s
    1.18
    oretically
    1.14
    ️
    1.05
    er
    1.03
    ly
    1.00
    ে
    0.99
    xiety
    0.94
    ed
    0.93
    ي
    0.91
    ️⃣
    0.90
    POSITIVE LOGITS
    1
    0.68
    2
    0.67
    éléments
    0.65
    $(
    0.64
    3
    0.62
    $-
    0.62
    foreach
    0.61
    przy
    0.60
    indeed
    0.60
    ρυθ
    0.59
    Activations Density 0.550%

    No Known Activations