© 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. 146591
    Prev
    Next
    INDEX
    Explanations

    ease, release, or code syntax

    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
     propellers
    0.82
    prop
    0.74
     प्रो
    0.71
    ಲಾಗುತ್ತದೆ
    0.70
    ዞ
    0.69
     Biên
    0.69
    ТА
    0.68
    propagation
    0.68
     तेंदुलकर
    0.68
     prop
    0.68
    POSITIVE LOGITS
     Основ
    0.70
     gu
    0.67
    啞
    0.67
     поду
    0.66
     trwa
    0.65
     rn
    0.64
     gs
    0.64
     START
    0.64
     pool
    0.63
    rn
    0.63
    Activations Density 0.001%

    No Known Activations