© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15324
    Prev
    Next
    INDEX
    Explanations

    HTML headings

    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
    ্স
    0.76
    ो
    0.71
     Entretanto
    0.70
    ী
    0.67
    炯
    0.63
     ต
    0.62
    ীষ
    0.61
    ։
    0.61
    奧
    0.60
    лия
    0.59
    POSITIVE LOGITS
     substring
    0.71
    ことが多い
    0.68
     bicarbon
    0.65
     subsequ
    0.61
    𝖒
    0.61
     exig
    0.61
     scraped
    0.61
     decrement
    0.61
    前者
    0.61
     piezo
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.