© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5394
    Prev
    Next
    INDEX
    Explanations

    correct database context

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

    The neuron fires on descriptive modifiers—especially longer, less common adjectives.

    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
    ındaki
    0.87
    が無い
    0.81
    ới
    0.72
     khắp
    0.72
    ností
    0.71
     thoſe
    0.71
    Һ
    0.71
    dyž
    0.70
     некоторых
    0.69
     sommige
    0.69
    POSITIVE LOGITS
     (!)
    0.82
    種類の
    0.72
    (!)
    0.72
    সংখ্যক
    0.71
     version
    0.70
     but
    0.69
     Fédération
    0.68
    ,
    0.68
     non
    0.66
     combination
    0.66
    Activations Density 0.507%

    No Known Activations