© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4322
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to physical‐movement/direction terms in exercise instructions (e.g. “up,” “down,” “back,” “stand,” “bend”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     phag
    0.91
    '
    0.88
    囡
    0.88
     ANN
    0.83
     cutaneous
    0.82
     spoken
    0.80
     PREC
    0.79
    ודי
    0.78
     види
    0.78
     huid
    0.78
    POSITIVE LOGITS
    Heights
    1.31
     height
    1.30
    height
    1.28
     heights
    1.24
     stairs
    1.23
     altura
    1.22
    梯
    1.18
    Height
    1.16
     Climb
    1.13
     tallest
    1.13
    Activations Density 2.178%

    No Known Activations