© 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. 9529
    Prev
    Next
    INDEX
    Explanations

    Node.js

    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
    ية
    2.66
    क
    2.36
    ف
    2.34
    ح
    2.05
     וכ
    1.87
    ق
    1.85
    ])).
    1.78
    न
    1.77
    ist
    1.71
    اد
    1.65
    POSITIVE LOGITS
    ように
    2.09
    因此
    1.96
    🄴
    1.95
    𝘮
    1.84
    લાઈ
    1.84
    ぅ
    1.83
    あれば
    1.79
     ktoré
    1.72
     불구하고
    1.72
     وعلى
    1.71
    Activations Density 0.054%

    No Known Activations