© 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. 146671
    Prev
    Next
    INDEX
    Explanations

    John Tyler

    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
    विद्यालय
    0.85
    :<
    0.80
    ంబేద్
    0.79
     Ricardo
    0.76
    味料
    0.75
     topped
    0.74
     Tomas
    0.73
     etched
    0.72
    ਚ
    0.72
     rediscovered
    0.71
    POSITIVE LOGITS
    leet
    0.67
     pol
    0.65
    ूज
    0.65
    lafen
    0.64
    得到了
    0.63
    নীয়
    0.63
     fontos
    0.63
     sinnvoll
    0.63
     CEOs
    0.62
    য়োজনীয়
    0.62
    Activations Density 0.000%

    No Known Activations