© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 11059
    Prev
    Next
    INDEX
    Explanations

    unexpected something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     but
    0.70
     accordingly
    0.60
    but
    0.57
    良好
    0.55
    )}
    0.54
    /
    0.52
    したがって
    0.52
    装备
    0.51
    ;$
    0.51
    -
    0.51
    POSITIVE LOGITS
     dennoch
    0.98
     మాత్రం
    0.95
    卻
    0.87
     trotzdem
    0.81
     Nonetheless
    0.80
    却
    0.80
     nonetheless
    0.79
     ANOTHER
    0.79
    却是
    0.79
     नहीं
    0.78
    Activations Density 0.002%

    No Known Activations