© 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. 9299
    Prev
    Next
    INDEX
    Explanations

    theorem statements

    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
    ی
    2.45
    a
    2.22
    یہ
    1.94
    یف
    1.91
    یه
    1.88
    ‌ای
    1.85
    fahrer
    1.74
    یط
    1.73
    یە
    1.70
     Außerdem
    1.69
    POSITIVE LOGITS
    IM
    1.65
    J
    1.52
    으로
    1.51
    FRE
    1.48
     préoccup
    1.44
    LE
    1.43
     використову
    1.41
    IG
    1.39
     sociaux
    1.38
    сть
    1.38
    Activations Density 0.001%

    No Known Activations