© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6513
    Prev
    Next
    INDEX
    Explanations

    pushing or grabbing

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

    The neuron detects imperative motion verbs describing physical actions of pushing or lifting (e.g., “push down,” “lift up”).

    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
     wits
    0.59
     transporte
    0.58
    e
    0.58
     minutos
    0.56
     tüm
    0.55
     Hearts
    0.55
    s
    0.55
     día
    0.54
    第二天
    0.54
    l
    0.54
    POSITIVE LOGITS
    KeyState
    0.59
     leverage
    0.58
     leverages
    0.57
     forcefully
    0.57
    ImageBeforeText
    0.56
    certificado
    0.56
     axiom
    0.55
    DATUM
    0.54
     baseless
    0.54
     foothold
    0.52
    Activations Density 0.003%

    No Known Activations