© 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. 13406
    Prev
    Next
    INDEX
    Explanations

    convenient ways

    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
    í
    2.47
    ד
    1.94
    ud
    1.93
    ñ
    1.88
    ’
    1.88
    å
    1.84
    ية
    1.80
    та
    1.78
    ü
    1.78
    émie
    1.77
    POSITIVE LOGITS
    orso
    1.89
    Conven
    1.65
     सारी
    1.48
    ไฟฟ้า
    1.43
    ம்
    1.41
     convenience
    1.40
    यॉर्क
    1.40
    น่า
    1.39
     სახელ
    1.38
    মিস্ট
    1.38
    Activations Density 0.075%

    No Known Activations