Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 109583
    Prev
    Next
    INDEX
    Explanations

    describes a condition or outcome

    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
    ियों
    0.87
    یت
    0.85
    ي
    0.79
    ার্স
    0.78
     Became
    0.75
    یکا
    0.73
    दर्शी
    0.73
    iyan
    0.73
     Tokugawa
    0.73
    TreeNavigator
    0.72
    POSITIVE LOGITS
     orice
    0.94
    n
    0.85
     qualquer
    0.82
     faut
    0.79
     spune
    0.78
    к
    0.77
     octombrie
    0.75
     profit
    0.75
     cualquier
    0.74
     você
    0.72
    Activations Density 0.000%

    No Known Activations