© 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. 41616
    Prev
    Next
    INDEX
    Explanations

    allows for

    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
    ों
    1.72
    te
    1.66
     exactement
    1.48
    //
    1.45
     vertes
    1.44
     власть
    1.43
     trasero
    1.41
     renforcer
    1.38
     inizi
    1.37
     certainement
    1.34
    POSITIVE LOGITS
    ي
    1.78
     exaggerate
    1.69
    ال
    1.66
    트
    1.66
     equaling
    1.63
    тические
    1.62
    皞
    1.59
    ти
    1.54
    ্রিক
    1.54
    तुरंग
    1.50
    Activations Density 0.008%

    No Known Activations