© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    inclusion criteria

    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
    ী
    2.75
    quele
    2.50
    ist
    2.42
    ل
    2.39
    ية
    2.36
    ian
    2.30
    ності
    2.22
    ার
    2.17
    de
    2.14
    er
    2.06
    POSITIVE LOGITS
    ا
    4.59
    い
    3.75
    ı
    3.66
    า
    3.48
    าค
    3.09
    نا
    2.73
    ่
    2.53
    ्स
    2.45
    ς
    2.41
    স
    2.33
    Activations Density 0.249%

    No Known Activations