© 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. 11640
    Prev
    Next
    INDEX
    Explanations

    author identification

    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
    ب
    2.48
    ي
    2.20
    ل
    2.14
    validator
    2.09
    י
    2.08
    y
    2.05
    e
    2.00
    م
    1.93
    د
    1.91
    ル
    1.90
    POSITIVE LOGITS
    stwa
    2.05
    asjon
    1.99
    lığ
    1.93
     bioquímica
    1.88
    speople
    1.87
    ství
    1.85
    на
    1.80
     inade
    1.78
     roue
    1.77
    名の
    1.71
    Activations Density 0.009%

    No Known Activations