© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    free time activities and hobbies

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

    The neuron strongly fires on the very first token of a new sentence (typically capitalized words or numbers at sentence boundaries).

    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_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
    녔
    0.60
    Mid
    0.54
    وكان
    0.54
    INN
    0.53
    ϋ
    0.52
     كانت
    0.51
     وكانت
    0.51
    iyordu
    0.51
    ങ്ങിയ
    0.50
    卿
    0.50
    POSITIVE LOGITS
     off
    1.59
     leisure
    1.59
     Off
    1.38
     Freizeit
    1.34
     Leisure
    1.30
    Off
    1.26
     OFF
    1.23
     offseason
    1.21
    off
    1.17
     hobbies
    1.17
    Activations Density 0.232%

    No Known Activations