© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6124
    Prev
    Next
    INDEX
    Explanations

    possessives and plurals

    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
    ו
    2.14
    nement
    2.11
    iation
    2.08
    ки
    2.06
    서
    2.03
    특별시
    1.98
    zelfde
    1.96
    های
    1.88
    মাত্র
    1.85
    сть
    1.82
    POSITIVE LOGITS
    ING
    1.80
    ージャー
    1.70
    ből
    1.52
     siphon
    1.50
     اتارنا
    1.50
    𝙿
    1.43
     ’
    1.41
     évident
    1.37
     catalyzed
    1.34
     sauté
    1.34
    Activations Density 1.002%

    No Known Activations