© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10878
    Prev
    Next
    INDEX
    Explanations

    formulas and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     tid
    0.46
     하나의
    0.43
     положи
    0.38
     รู้
    0.38
     wrongs
    0.38
     idem
    0.38
     escena
    0.38
     일
    0.37
    })}\
    0.37
     어떤
    0.37
    POSITIVE LOGITS
    ﺡ
    0.43
    supabase
    0.42
    柤
    0.40
    枼
    0.39
    ူ
    0.39
     технологі
    0.38
    Berat
    0.38
    酽
    0.38
     technolog
    0.38
     tecnologie
    0.38
    Activations Density 0.015%

    No Known Activations