© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11106
    Prev
    Next
    INDEX
    Explanations

    lawyer and philosopher

    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_9_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
    k
    2.53
    ात
    2.41
    ्डा
    2.37
    ار
    2.29
    től
    2.25
    tól
    2.21
    مال
    2.20
    epe
    2.20
    anego
    2.17
    деся
    2.17
    POSITIVE LOGITS
    人
    2.23
    е
    2.15
    у
    2.13
    🏻
    2.12
    🏼
    2.03
    ता
    1.98
    ங்கிணை
    1.95
    ся
    1.87
    jaa
    1.86
    ש
    1.85
    Activations Density 0.039%

    No Known Activations