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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53022
    Prev
    Next
    INDEX
    Explanations

    terms of endearment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    嗌
    0.78
    然后在
    0.73
     وتم
    0.71
    するのが
    0.69
     موجوده
    0.68
     హీరోయి
    0.68
    ')));
    0.67
     रहीं
    0.67
    攷
    0.67
    ക്കുകയും
    0.66
    POSITIVE LOGITS
     dear
    1.20
    please
    1.16
     mío
    1.06
     عزیز
    1.01
    ர்களே
    0.99
    dear
    0.98
     please
    0.96
    ,"
    0.96
     dearest
    0.95
     contraire
    0.94
    Activations Density 0.017%

    No Known Activations