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

    Neuronpedia

    Jacobian LensNEW
    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. 13209
    Prev
    Next
    INDEX
    Explanations

    describing what someone is wearing

    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
    📈
    1.00
     integrable
    0.93
    会导致
    0.91
     działalności
    0.87
     அதிகரிக்கும்
    0.87
     செய்யப்படும்
    0.86
     afecta
    0.86
    🏞
    0.85
     logarithm
    0.83
     применяется
    0.83
    POSITIVE LOGITS
     dressed
    1.92
    dressed
    1.67
     wearing
    1.63
    wearing
    1.50
    穿着
    1.48
    Wearing
    1.45
     Wearing
    1.40
     clad
    1.36
     wore
    1.36
     armed
    1.34
    Activations Density 0.085%

    No Known Activations