© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15174
    Prev
    Next
    INDEX
    Explanations

    capitalized words and phrases

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

    This neuron responds to floating-point numeric tokens—especially the “offered <number>:” values in directory or business listing entries.

    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
    Datasets
    0.81
    <0x86>
    0.75
    খ্যান
    0.75
     त्रास
    0.73
     తీవ్ర
    0.72
    PCs
    0.71
     genome
    0.70
     voxel
    0.69
    owo
    0.68
     feiern
    0.68
    POSITIVE LOGITS
    sí
    0.86
    秶
    0.82
    ء
    0.82
    ର୍
    0.81
    䅞
    0.81
     eleg
    0.80
    ض
    0.79
    祺
    0.79
    BRANCH
    0.77
     irá
    0.74
    Activations Density 0.001%

    No Known Activations