© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    why they're good

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

    The neuron most strongly activates on the auxiliary “will” (and its immediate verb), i.e. marking future‐tense constructions.

    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
    Año
    0.82
    Фа
    0.78
     Polícia
    0.76
    Alert
    0.75
    на
    0.73
     vốn
    0.73
    ToJson
    0.71
    덬
    0.71
    Traité
    0.70
    AlertDialog
    0.69
    POSITIVE LOGITS
    arness
    0.77
    ிட்ட
    0.75
    erms
    0.75
    trif
    0.75
    verts
    0.75
    shin
    0.74
    OMO
    0.74
    permal
    0.73
    ол
    0.72
    ங்களை
    0.71
    Activations Density 0.000%

    No Known Activations