© 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. 5317
    Prev
    Next
    INDEX
    Explanations

    the presence of numeric expressions or numbers (tokens that are part of numeric quantities).

    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
    edTest
    0.74
    '
    0.73
    scan
    0.71
    iance
    0.71
    FALSE
    0.70
    <0x0D>
    0.70
    IDENT
    0.70
    CHICAGO
    0.69
    lar
    0.68
    fps
    0.68
    POSITIVE LOGITS
     Städ
    0.88
     culminating
    0.81
    লাষ
    0.80
     atth
    0.78
     billionaires
    0.78
     culminates
    0.78
     zes
    0.76
     diventare
    0.75
     montañas
    0.73
    蕞
    0.73
    Activations Density 0.000%

    No Known Activations