© 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. 5917
    Prev
    Next
    INDEX
    Explanations

    within the

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens, identifying numbers and number‐like strings 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_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
    。
    1.11
    。《
    1.05
    ۔
    0.98
    》。
    0.97
    。「
    0.95
    €.
    0.95
    ។
    0.93
     。
    0.92
    。『
    0.92
    ）。
    0.92
    POSITIVE LOGITS
     during
    1.79
     on
    1.43
     when
    1.42
     katika
    1.41
     tijdens
    1.41
     after
    1.41
     throughout
    1.38
     durante
    1.38
     στις
    1.37
     within
    1.35
    Activations Density 0.896%

    No Known Activations