© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12675
    Prev
    Next
    INDEX
    Explanations

    Client secret

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

    This neuron responds to relatively uncommon, content‐bearing words (technical terms, descriptors, and proper nouns) rather than common function words.

    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
     collabor
    0.80
    вете
    0.80
    呲
    0.79
     services
    0.77
    нове
    0.77
     neph
    0.77
     equivoc
    0.77
     programmes
    0.75
    गेड
    0.75
     multinationals
    0.75
    POSITIVE LOGITS
     Jeśli
    0.89
    
    0.86
    šla
    0.82
     Ва
    0.78
    čit
    0.77
    ði
    0.76
     Sting
    0.75
     Was
    0.74
    ASI
    0.74
    Pablo
    0.73
    Activations Density 0.000%

    No Known Activations