© 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. 1883
    Prev
    Next
    INDEX
    Explanations

    health and finance terms

    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
     trend
    0.82
     ploy
    0.75
    trend
    0.73
     multim
    0.72
     implication
    0.70
     endExpNow
    0.70
    倸
    0.68
     MULT
    0.68
    MULT
    0.68
     allocations
    0.68
    POSITIVE LOGITS
     Characteristics
    0.77
    Characteristics
    0.68
    ंपरा
    0.65
     ಸ್ನೇಹಿತ
    0.64
    힐
    0.63
    hetra
    0.62
    adType
    0.62
    Ley
    0.62
    Características
    0.62
    Substring
    0.62
    Activations Density 0.000%

    No Known Activations