© 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-262K
    7. 4499
    Prev
    Next
    INDEX
    Explanations

    internal clock

    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
     verursacht
    1.10
     realizando
    1.04
     reduzir
    0.97
     höhere
    0.92
    льский
    0.89
     produzir
    0.89
     학
    0.88
    ය
    0.86
     또한
    0.86
     причины
    0.86
    POSITIVE LOGITS
    lib
    0.80
    شان
    0.75
    oi
    0.74
     cherry
    0.73
    ♥
    0.71
    SOUTH
    0.71
    g
    0.71
    ('-
    0.70
    al
    0.70
     salwar
    0.69
    Activations Density 0.000%

    No Known Activations