© 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-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 46220
    Prev
    Next
    INDEX
    Explanations

    those goals

    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_16_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
    فون
    0.45
    جي
    0.45
     escuela
    0.43
    정
    0.43
     capitán
    0.43
     propietarios
    0.42
     boz
    0.42
     fortaleza
    0.42
    글
    0.42
     recht
    0.41
    POSITIVE LOGITS
     पुनर्
    0.63
    larını
    0.58
    inated
    0.54
    ‌ی
    0.54
     nitrification
    0.52
    illation
    0.50
    lation
    0.50
     વધ
    0.49
    bation
    0.49
    dfe
    0.48
    Activations Density 0.000%

    No Known Activations