© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13882
    Prev
    Next
    INDEX
    Explanations

    footwear and feet

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

    footwear, toes, 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_16k_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
    getDrawable
    0.52
    胸
    0.51
    扛
    0.51
     胸
    0.47
     pector
    0.44
    肩
    0.44
    raphene
    0.44
    滸
    0.43
    Beyblade
    0.43
    უტ
    0.43
    POSITIVE LOGITS
     footwear
    1.29
    🦶
    1.25
     toes
    1.24
     barefoot
    1.24
     shoes
    1.23
     foot
    1.22
     toe
    1.21
     Shoe
    1.21
     shoe
    1.20
     靴
    1.19
    Activations Density 0.427%

    No Known Activations