© 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. 24-GEMMASCOPE-2-RES-262K
    7. 553
    Prev
    Next
    INDEX
    Explanations

    time periods and associated numbers

    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_24_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
    コン
    0.70
    Ⅼ
    0.68
    堌
    0.65
    Одна
    0.64
    ダウンロード
    0.63
     inmediata
    0.63
    এ
    0.63
    アプリケーション
    0.62
    ทัน
    0.62
    CurrentImageData
    0.61
    POSITIVE LOGITS
     was
    0.76
     Overall
    0.73
     overall
    0.68
    빴
    0.67
     wasn
    0.64
     Monsters
    0.64
     olmasına
    0.63
     było
    0.63
    overall
    0.62
    웠
    0.62
    Activations Density 0.001%

    No Known Activations