© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19767
    Prev
    Next
    INDEX
    Explanations

    then someone arrived

    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_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
    俬
    0.83
     للد
    0.81
     डाउट्स
    0.81
    亍
    0.80
     عند
    0.79
    褔
    0.78
     nawet
    0.78
     viktigt
    0.77
    (...
    0.77
    喡
    0.76
    POSITIVE LOGITS
     planche
    0.63
     scrap
    0.63
     Val
    0.63
     Cone
    0.62
    Math
    0.62
    Colorful
    0.61
    สวย
    0.61
     Yes
    0.61
    Resizable
    0.60
     Pare
    0.60
    Activations Density 0.001%

    No Known Activations