© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 14492
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ם
    1.27
    ان
    1.15
    انج
    1.03
    دة
    1.02
    mış
    1.02
    ból
    1.02
    ことで
    1.01
    ्स
    0.95
     hammering
    0.95
    ają
    0.94
    POSITIVE LOGITS
    ↵
    1.25
     Nutrient
    0.89
    q
    0.89
    platforms
    0.85
     Schad
    0.84
    蜢
    0.84
    ✮
    0.83
    workouts
    0.83
     promov
    0.82
    Shirts
    0.82
    Activations Density 0.005%

    No Known Activations