© 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-262K
    7. 146729
    Prev
    Next
    INDEX
    Explanations

    computer terms and Russian

    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
    ებ
    0.74
    स्टार
    0.68
    ربع
    0.67
     Everton
    0.67
     Diagnostic
    0.65
    睗
    0.65
    وروب
    0.65
    海上
    0.64
     problémy
    0.64
    نائي
    0.64
    POSITIVE LOGITS
    INIT
    0.70
     память
    0.66
    li
    0.59
    ӧ
    0.59
     lip
    0.59
     slippery
    0.59
     intervening
    0.58
     السياسي
    0.57
     initiating
    0.57
    tan
    0.57
    Activations Density 0.002%

    No Known Activations