© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2373
    Prev
    Next
    INDEX
    Explanations

    y = linspace

    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
    Not in Any Lists

    No Comments

    Negative Logits
    䤚
    0.76
    㣫
    0.75
    ்சி
    0.74
    iyim
    0.74
    囵
    0.72
     Hopl
    0.71
     ويكيپيديا
    0.71
    隀
    0.71
     Kyi
    0.71
     Rhys
    0.70
    POSITIVE LOGITS
     בא
    1.15
    ama
    1.04
    awać
    1.01
     לא
    0.99
    amatan
    0.99
    aban
    0.97
    aacute
    0.97
    א
    0.96
    aza
    0.95
    ają
    0.95
    Activations Density 2.704%

    No Known Activations