© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14142
    Prev
    Next
    INDEX
    Explanations

    style and fashion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    䣬
    1.44
    <unused823>
    1.39
    𒌵
    1.35
    
    1.34
    <unused12>
    1.33
    <unused21>
    1.31
    imcoords
    1.30
    𒐁
    1.28
    <unused1575>
    1.28
    opencamer
    1.28
    POSITIVE LOGITS
    ↵↵
    1.04
     Fashion
    0.87
     fashion
    0.77
     Page
    0.75
      
    0.72
     Wedding
    0.70
    mai
    0.69
     Theme
    0.69
     Style
    0.69
    tem
    0.68
    Activations Density 0.000%

    No Known Activations