© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 724
    Prev
    Next
    INDEX
    Explanations

    lists and actions

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

    The neuron fires on verbs that denote active support, nurturing, dissemination, or generation (e.g., “supporting,” “nurture,” “generate,” “disseminate,” “present”).

    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
     ();
    0.45
     ؛
    0.44
     가서
    0.44
     ;
    0.44
    ；
    0.41
     నుంచి
    0.41
     kerana
    0.39
     membuatnya
    0.39
     ;\
    0.39
     segítség
    0.38
    POSITIVE LOGITS
    rogens
    0.65
    /
    0.54
    甚至
    0.52
     hatta
    0.49
     indeed
    0.48
     anzi
    0.47
     bahkan
    0.46
    ROID
    0.46
    /'.$
    0.45
    rology
    0.44
    Activations Density 0.500%

    No Known Activations