© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens containing numeric digits (i.e. numbers or year-like values).

    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
     Erklärung
    0.40
     영화
    0.38
     Ș
    0.38
     Geschä
    0.37
    唰
    0.37
     Veränder
    0.37
     Thyroid
    0.36
    RAchievement
    0.36
     asesin
    0.35
    と思われる
    0.34
    POSITIVE LOGITS
    ;
    0.44
    .
    0.43
    outil
    0.41
    se
    0.40
    utani
    0.39
    ный
    0.38
    2
    0.38
    erm
    0.38
    ím
    0.38
    ogs
    0.38
    Activations Density 0.000%

    No Known Activations