© 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. 4756
    Prev
    Next
    INDEX
    Explanations

    start or wait until

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

    The neuron is essentially a numeric‐value detector—it lights up strongly whenever it encounters a multi‐digit (and especially decimal) number token.

    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
     👋
    0.78
    ﻱ
    0.73
     shareholders
    0.72
     $=\
    0.72
     apologized
    0.72
     Беларусь
    0.71
     encoders
    0.71
     單
    0.71
     },
    0.71
     architectures
    0.71
    POSITIVE LOGITS
    それを
    0.81
    ن
    0.78
     raza
    0.75
    eks
    0.74
    nich
    0.73
     nuevos
    0.72
     réun
    0.71
     berdiri
    0.71
    ِ
    0.70
    ມັນ
    0.70
    Activations Density 0.001%

    No Known Activations