© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 68688
    Prev
    Next
    INDEX
    Explanations

    socks and legwear

    np_acts-logits-general · gemini-2.5-flash-lite

    underwear and socks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nhiễm
    0.47
    BlogPost
    0.47
    ยิน
    0.45
    樵
    0.44
     मेथड
    0.43
    赞
    0.43
    通行
    0.42
    colgroup
    0.42
    緯
    0.42
     मौ
    0.41
    POSITIVE LOGITS
     underwear
    0.89
     panties
    0.81
     socks
    0.80
     lingerie
    0.75
    underwear
    0.71
     Socks
    0.71
     stockings
    0.70
     sock
    0.68
     leggings
    0.67
     stocking
    0.64
    Activations Density 0.128%

    No Known Activations