© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24497
    Prev
    Next
    INDEX
    Explanations

    barefoot walking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     álgebra
    0.40
     పొ
    0.40
    合金
    0.40
    壘
    0.39
    coprote
    0.37
    オル
    0.37
     methodical
    0.37
    典
    0.37
    িল
    0.36
    匠
    0.36
    POSITIVE LOGITS
     Bare
    0.75
    Bare
    0.74
     bare
    0.71
     barefoot
    0.65
    bare
    0.62
     naked
    0.57
    naked
    0.54
     Naked
    0.50
     shirtless
    0.50
     nudity
    0.46
    Activations Density 0.003%

    No Known Activations