© 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. 3340
    Prev
    Next
    INDEX
    Explanations

    insights into

    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
     carbides
    1.97
    预防
    1.80
     haunts
    1.72
    ケーション
    1.68
    ванням
    1.67
    のである
    1.59
    疣
    1.58
    LLO
    1.57
    旨在
    1.56
    ため
    1.55
    POSITIVE LOGITS
     tandis
    1.80
    ö
    1.77
    тран
    1.74
    ور
    1.61
    TE
    1.59
    که
    1.58
    ္ဂ
    1.55
    вет
    1.52
    ből
    1.50
    ą
    1.48
    Activations Density 0.006%

    No Known Activations