© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3167
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (integers, decimals, version numbers, IP addresses, and other number-like strings).

    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_31_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
     mérid
    0.61
     kurulum
    0.61
     
    0.60
     nový
    0.60
     Kauai
    0.60
     herkese
    0.58
     ∗
    0.56
     núcleos
    0.56
     probleml
    0.55
     Steck
    0.55
    POSITIVE LOGITS
    //}
    0.89
     //}
    0.74
    //
    0.66
    //{
    0.58
    /}{
    0.56
    ũng
    0.56
     عشق
    0.54
    ilinear
    0.53
    Anita
    0.52
    |}{
    0.52
    Activations Density 0.010%

    No Known Activations