© 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. 14002
    Prev
    Next
    INDEX
    Explanations

    defines target workbook

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

    The neuron detects floating-point numeric tokens—numbers expressed with decimal points.

    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
    ور
    0.75
    rror
    0.75
    ec
    0.74
    హ
    0.73
    ński
    0.72
     cercando
    0.71
    uiDesigner
    0.71
    ي
    0.71
    呿
    0.71
    aż
    0.70
    POSITIVE LOGITS
     Hacer
    0.96
     MgO
    0.85
     나오
    0.84
     나오는
    0.82
     kavram
    0.81
    ﻊ
    0.79
     lyrical
    0.77
     Sparse
    0.76
     Thee
    0.75
    ﻼ
    0.74
    Activations Density 0.001%

    No Known Activations