© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for numeric values (tokens containing digits or number-like measurements).

    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
    észeti
    0.61
    ஃப
    0.53
    Ꮂ
    0.53
    最初は
    0.52
    iforn
    0.51
    intai
    0.47
    φυ
    0.46
    {[
    0.45
    ij
    0.45
    事前に
    0.45
    POSITIVE LOGITS
     again
    5.63
    again
    5.13
     AGAIN
    5.00
     Again
    4.94
     novamente
    4.94
    Again
    4.84
     nuevamente
    4.69
     снова
    4.59
     опять
    4.53
    再び
    4.50
    Activations Density 2.015%

    No Known Activations