© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    continue/start action

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

    The neuron strongly activates on words that describe driving actions or situations in traffic (e.g. stopping at traffic lights, driving at specified speeds).

    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
    ,
    0.77
     heretofore
    0.74
    B
    0.73
    ﾕ
    0.73
    --
    0.71
    OL
    0.70
    on
    0.67
     muß
    0.67
    J
    0.67
    
    0.67
    POSITIVE LOGITS
     idk
    1.41
    🥹
    1.10
     ahí
    1.07
     hehe
    1.06
     haha
    1.05
    🥲
    1.05
    🫶
    1.04
    🫠
    1.00
     hahaha
    0.99
    🫡
    0.96
    Activations Density 0.078%

    No Known Activations