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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10595
    Prev
    Next
    INDEX
    Explanations

    fingers, thumbs, and toes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    腰
    1.04
     mochila
    0.99
     Legs
    0.97
     legs
    0.97
     腰
    0.95
    郯
    0.94
     épaules
    0.93
    ર્મ
    0.91
    稈
    0.90
     Shoulder
    0.90
    POSITIVE LOGITS
     phal
    1.38
    index
    1.21
     index
    1.19
    Index
    1.17
     Index
    1.10
     finger
    1.09
     pink
    1.09
    指
    1.08
     indice
    1.06
    INDEX
    1.03
    Activations Density 0.186%

    No Known Activations