© 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. 12374
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations

    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
     comprobar
    0.60
    ﾍ
    0.59
     ওয়ালপেপার
    0.58
     รอ
    0.58
     glyphicon
    0.57
    ipkan
    0.57
    ส์
    0.57
     শিবির
    0.56
     WebElement
    0.55
     /**
    0.55
    POSITIVE LOGITS
     starry
    0.63
     treetops
    0.61
     Daph
    0.60
     څرنګ
    0.60
     पद्ध
    0.59
     rodent
    0.59
     hänen
    0.59
     Stéphane
    0.59
     glorious
    0.58
     Marcell
    0.58
    Activations Density 0.049%

    No Known Activations