© 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. 3006
    Prev
    Next
    INDEX
    Explanations

    internal focus and energy

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

    The neuron is specialized to pick out words relating to movement, travel, or spatial displacement.

    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
     ৩৮
    0.71
    4
    0.70
    9
    0.69
     அனைவரும்
    0.68
     ৩৭
    0.66
    COMMON
    0.65
     FHWA
    0.64
    ๔
    0.64
     sempurna
    0.64
    등급
    0.64
    POSITIVE LOGITS
     distractions
    0.98
     bisschen
    0.96
     allerlei
    0.94
     infections
    0.93
     इलाकों
    0.90
    atividade
    0.88
     errands
    0.88
     ఎక్కువగా
    0.88
     activités
    0.88
     পড়াশ
    0.87
    Activations Density 0.512%

    No Known Activations