© 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. 10844
    Prev
    Next
    INDEX
    Explanations

    parameter definitions

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

    The neuron fires on numeric expressions—especially decimal numbers—i.e. measurements, quantities, or other floating-point values.

    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
    𝒆
    0.75
    ạch
    0.70
    ibraries
    0.69
    ợ
    0.68
    ات
    0.67
    喝酒
    0.66
    ند
    0.65
    ája
    0.65
    वीं
    0.62
     payer
    0.62
    POSITIVE LOGITS
     ഖ
    0.84
    ﻤ
    0.80
    varande
    0.77
    galkan
    0.76
     கோ
    0.75
    cription
    0.75
    เท
    0.73
     যুক্তরাষ্ট্রে
    0.73
    食べた
    0.73
    limegreen
    0.72
    Activations Density 0.000%

    No Known Activations