© 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. 12-GEMMASCOPE-2-RES-262K
    7. 10433
    Prev
    Next
    INDEX
    Explanations

    if __name__ ==

    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_12_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
    ە
    0.95
    い
    0.89
    این
    0.82
     solche
    0.82
    ให้
    0.81
    ą
    0.81
    }$;
    0.80
    ز
    0.80
    ដែល
    0.75
    }$.
    0.74
    POSITIVE LOGITS
     kinks
    0.83
     pests
    0.68
     poets
    0.67
     tenets
    0.64
     asteroids
    0.63
     DFS
    0.63
     GED
    0.62
     ans
    0.62
     ANOVA
    0.61
     Zeus
    0.61
    Activations Density 0.086%

    No Known Activations