© 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. 145373
    Prev
    Next
    INDEX
    Explanations

    explanation of a definition

    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
     jong
    0.71
     hoff
    0.71
    Anagram
    0.69
    webElementGuid
    0.69
    pecia
    0.69
     ხ
    0.66
     szüks
    0.66
    カフェ
    0.65
    糠
    0.65
    CAST
    0.65
    POSITIVE LOGITS
     crime
    0.85
     Fiscal
    0.75
     проек
    0.73
     Designed
    0.73
     Crime
    0.72
     whining
    0.72
    ለመ
    0.72
     Stu
    0.72
     তাহাদিগকে
    0.72
     Brim
    0.72
    Activations Density 0.000%

    No Known Activations