© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3796
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on numeric tokens or sequences of digits in the text.

    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
    http
    1.40
     xrange
    1.38
    ట్స్‌మన్
    1.16
     http
    1.11
     ব্যাটসম্যান
    1.05
     muß
    0.95
     চিকিত
    0.90
    
    0.90
    􀂃
    0.90
     করোনাভাই
    0.89
    POSITIVE LOGITS
     TikTok
    2.72
     ChatGPT
    2.67
     ২০২৩
    2.50
    🫶
    2.41
     metaverse
    2.34
    TikTok
    2.33
    🥹
    2.33
    ChatGPT
    2.28
    🫡
    2.27
     Metaverse
    2.25
    Activations Density 0.396%

    No Known Activations