© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12462
    Prev
    Next
    INDEX
    Explanations

    `=` or `set`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    나
    0.86
    viet
    0.83
    스
    0.81
    ių
    0.79
    有时候
    0.79
    Tổng
    0.79
     定义
    0.78
     одна
    0.77
     제주
    0.77
    误
    0.75
    POSITIVE LOGITS
     Hin
    0.77
     amenities
    0.75
     Sax
    0.73
     Hearts
    0.72
     excesses
    0.72
     وبي
    0.72
     saxophone
    0.71
     hearts
    0.70
     binoculars
    0.70
     Wonderland
    0.68
    Activations Density 0.000%

    No Known Activations