© 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-16K
    7. 5153
    Prev
    Next
    INDEX
    Explanations

    requesting to provide

    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_16k_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
    OM
    2.33
    ों
    2.27
    ات
    1.94
    ség
    1.84
    s
    1.84
    rigley
    1.83
    만
    1.79
    க்
    1.77
    ्स
    1.73
    tedir
    1.73
    POSITIVE LOGITS
    kannya
    1.95
    us
    1.91
    é
    1.90
    le
    1.76
    ina
    1.71
    ir
    1.68
    te
    1.67
    та
    1.67
    k
    1.65
    ين
    1.64
    Activations Density 0.149%

    No Known Activations