© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14123
    Prev
    Next
    INDEX
    Explanations

    reactive gameplay, relative frequencies, talking me through, political ideologies, different industries, visual diagrams, spending categories, print or write

    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
     $\|\
    0.78
    brief
    0.78
     ನೆಲಮಾಳಿಗೆ
    0.74
    crib
    0.74
    ہری
    0.72
    )_\
    0.71
    Brief
    0.71
    removeItem
    0.69
     Chakrab
    0.69
    찡
    0.68
    POSITIVE LOGITS
     www
    0.80
     created
    0.79
     pleasures
    0.71
     pastries
    0.70
     arranging
    0.69
     WWW
    0.69
     बुल
    0.68
    颜色
    0.67
     anlam
    0.67
     za
    0.67
    Activations Density 0.000%

    No Known Activations