© 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-262K
    7. 145488
    Prev
    Next
    INDEX
    Explanations

    self access attributes

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     بودم
    0.83
     perhaps
    0.81
     అ
    0.81
     داش
    0.80
     आपसे
    0.77
     אך
    0.75
    此
    0.75
     sought
    0.74
     solicita
    0.74
    此次
    0.73
    POSITIVE LOGITS
     organs
    0.80
     Inequality
    0.76
     quím
    0.74
     Tath
    0.71
     ecosystems
    0.70
     Around
    0.69
    वाधिकार
    0.69
    rypted
    0.69
    蜓
    0.69
     tokamak
    0.67
    Activations Density 0.002%

    No Known Activations