© 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. 15153
    Prev
    Next
    INDEX
    Explanations

    students per computer

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

    The neuron activates specifically on floating‐point numeric values (large measurements or statistics expressed as decimal numbers).

    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
    getConfiguration
    0.82
    шка
    0.80
    шку
    0.78
    ettings
    0.74
    т
    0.73
    шке
    0.71
    ica
    0.69
    inger
    0.69
    डेन
    0.69
    жета
    0.69
    POSITIVE LOGITS
     atividades
    0.97
     trabalho
    0.91
     lluvias
    0.90
     있는
    0.89
     actividades
    0.89
    ﾐ
    0.85
     である
    0.84
     중
    0.84
     도
    0.83
     coisas
    0.82
    Activations Density 0.000%

    No Known Activations