© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    numerical range separators

    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
    Negative Logits
    덟
    0.67
    相结合
    0.66
     کردن
    0.65
     />;
    0.63
     ہوئی
    0.63
    (_)
    0.62
    adə
    0.62
    冋
    0.60
    IfExists
    0.60
    டைந்த
    0.60
    POSITIVE LOGITS
     -
    2.08
    –
    1.94
    -$
    1.94
    -
    1.87
    °-
    1.59
    -"+
    1.54
    −
    1.53
    -'+
    1.50
    
    1.50
     –
    1.50
    Activations Density 0.779%

    No Known Activations