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. 22-GEMMASCOPE-2-RES-65K
    4. 4171
    Prev
    Next
    INDEX
    Explanations

    fun and humor

    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_22_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
     Normdatei
    0.82
    readthedocs
    0.82
     restructure
    0.80
    Blueprint
    0.74
    楔
    0.73
     Workbench
    0.70
     స్థాప
    0.68
     शक्तिशाली
    0.68
    靛
    0.68
     insuffis
    0.68
    POSITIVE LOGITS
     fun
    2.92
     amusing
    2.78
     enjoyable
    2.69
     entertaining
    2.66
     enjoyment
    2.64
     humorous
    2.63
     divertido
    2.61
     diversión
    2.56
    乐趣
    2.53
     entertainment
    2.50
    Activations Density 1.194%

    No Known Activations