© 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. 4499
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (e.g. digits and decimal‐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
     reimag
    1.38
     unapolog
    1.13
     livestream
    1.04
     LGBTQ
    1.02
     impactful
    1.01
     TikTok
    1.00
    怼
    0.98
     unwavering
    0.95
    所有人
    0.95
    TikTok
    0.93
    POSITIVE LOGITS
     physico
    1.18
     morphogenesis
    0.99
     geometrical
    0.96
    
    0.95
     calorimetric
    0.91
     MPEG
    0.91
     fdata
    0.91
     scanty
    0.91
     svm
    0.90
     subdir
    0.90
    Activations Density 0.212%

    No Known Activations