© 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. 41305
    Prev
    Next
    INDEX
    Explanations

    enables advancement or select

    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
    क
    2.14
    س
    2.05
    ক
    1.95
    க
    1.95
    ES
    1.81
    ේ
    1.78
    ك
    1.74
    కి
    1.65
    ला
    1.64
    이자
    1.63
    POSITIVE LOGITS
    arbeitet
    1.73
    iors
    1.70
    zicht
    1.64
    mäßig
    1.63
    mers
    1.63
    prints
    1.60
    volle
    1.58
    い
    1.57
    ać
    1.55
    aia
    1.53
    Activations Density 0.000%

    No Known Activations