© 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. 145734
    Prev
    Next
    INDEX
    Explanations

    user input prompts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     democracy
    0.84
     unsolicited
    0.83
    vergne
    0.78
    Ղ
    0.77
     faith
    0.77
    <unused2144>
    0.76
    telegram
    0.76
    emphasis
    0.76
    擞
    0.75
     accent
    0.75
    POSITIVE LOGITS
     macOS
    0.82
     Instantiate
    0.78
    كثر
    0.76
    они
    0.75
     iterate
    0.75
    ம்
    0.74
     版本
    0.73
    dı
    0.73
     mogli
    0.72
    대로
    0.71
    Activations Density 0.001%

    No Known Activations