© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    calendar days and times

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

    The neuron specifically detects numeric tokens that include decimal points (floating‐point 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
    ﻄ
    0.93
     Caedwalla
    0.90
    yar
    0.89
     Actualmente
    0.87
    yı
    0.87
     británico
    0.86
    y
    0.85
    yong
    0.81
     Ahora
    0.80
     basada
    0.80
    POSITIVE LOGITS
     каче
    0.75
    |$,
    0.73
     finely
    0.73
     उठा
    0.70
    geben
    0.68
     এজন্য
    0.67
    для
    0.66
    0.66
    стой
    0.66
     tiny
    0.65
    Activations Density 0.000%

    No Known Activations