© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42092
    Prev
    Next
    INDEX
    Explanations

    Crimea

    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
    س
    2.14
    speople
    1.74
    ים
    1.61
    ك
    1.54
    樑
    1.48
    ્સ
    1.46
    كال
    1.42
    gies
    1.41
    ierung
    1.40
    σετε
    1.40
    POSITIVE LOGITS
    ال
    2.25
    ار
    1.74
    ি
    1.73
    िमा
    1.56
    あえず
    1.55
    िरा
    1.51
    angleright
    1.51
    ام
    1.49
    ंशिक
    1.47
    id
    1.46
    Activations Density 0.001%

    No Known Activations