© 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. 42163
    Prev
    Next
    INDEX
    Explanations

    > paradigm shift

    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
    د
    2.64
    ur
    1.95
    o
    1.91
    ו
    1.89
     Résultats
    1.88
    e
    1.88
    ται
    1.86
    ت
    1.82
    л
    1.78
     communément
    1.76
    POSITIVE LOGITS
    cida
    1.52
    ushing
    1.47
    cible
    1.47
     in
    1.46
     believe
    1.45
    まっている
    1.43
     to
    1.41
     of
    1.40
     is
    1.39
     as
    1.39
    Activations Density 0.000%

    No Known Activations