© 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. 41428
    Prev
    Next
    INDEX
    Explanations

    input code or variable

    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
    ل
    2.52
    א
    2.48
    ہ
    2.30
    ל
    2.17
    তবে
    1.96
    يم
    1.92
    ৪
    1.91
    겅
    1.87
    ט
    1.84
    و
    1.84
    POSITIVE LOGITS
    ة
    2.31
    dalam
    1.94
     pleinement
    1.88
    
    1.84
     وبين
    1.80
    rechts
    1.73
     koska
    1.71
     sofern
    1.68
    ../
    1.66
     ausreiche
    1.66
    Activations Density 0.025%

    No Known Activations