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. 1080
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or amusement

    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
    athermy
    0.65
     удовольствием
    0.63
    Action
    0.62
     высокого
    0.62
    ACTION
    0.60
    action
    0.60
    $\--
    0.60
    intestin
    0.60
     것으로
    0.60
     fantástico
    0.59
    POSITIVE LOGITS
     lmao
    2.04
     lol
    1.48
     😂
    1.46
     tbh
    1.44
     😂😂
    1.38
    💀
    1.26
     idk
    1.25
     hahaha
    1.21
    ㅋㅋㅋㅋ
    1.20
     LOL
    1.18
    Activations Density 0.094%

    No Known Activations