© 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. 36598
    Prev
    Next
    INDEX
    Explanations

    thermo, severity

    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
    ли
    3.03
    서
    2.80
    ки
    2.48
    م
    2.41
    து
    2.36
    oretically
    2.36
    ש
    2.33
    ছেন
    2.28
    jų
    2.17
    ductory
    2.14
    POSITIVE LOGITS
    OREM
    1.85
    𝐄
    1.79
     وعلى
    1.76
    IK
    1.59
    を取得
    1.55
     in
    1.53
    اء
    1.48
     Conver
    1.47
    ᐟ
    1.45
    ologically
    1.41
    Activations Density 0.079%

    No Known Activations