© 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. 1852
    Prev
    Next
    INDEX
    Explanations

    SIGINT derived from

    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
    十分に
    0.81
    ंसह
    0.76
    が表示
    0.72
     충분
    0.71
    と共に
    0.70
    对其
    0.70
    ichever
    0.68
    colorbar
    0.67
    陪
    0.67
    Reasons
    0.67
    POSITIVE LOGITS
     involves
    3.60
     involve
    3.52
     involving
    2.65
     involved
    2.63
     melibatkan
    2.55
     envolve
    2.48
     entails
    2.30
     relies
    2.25
     revolves
    2.23
    涉及
    2.10
    Activations Density 2.483%

    No Known Activations