© 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. 9833
    Prev
    Next
    INDEX
    Explanations

    extreme

    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
    ية
    1.78
    ια
    1.76
    ά
    1.75
    ες
    1.72
    dır
    1.72
    ،
    1.70
    ன்
    1.70
    ۔
    1.66
    िकारक
    1.62
     girder
    1.62
    POSITIVE LOGITS
    ب
    2.50
    ما
    2.09
    א
    2.05
    ນ
    2.05
    ﻤ
    2.00
    ج
    1.99
    ﺠ
    1.91
     userRoutes
    1.91
    me
    1.89
    पंथी
    1.89
    Activations Density 0.046%

    No Known Activations