© 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. 12865
    Prev
    Next
    INDEX
    Explanations

    programming context syntax

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

    The neuron fires strongly on numeric tokens (integers or decimals).

    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
    έργ
    0.34
    名为
    0.33
    形状
    0.31
     dielectric
    0.31
    зик
    0.31
    держи
    0.30
    =&
    0.30
    ешься
    0.30
    らの
    0.30
    めの
    0.30
    POSITIVE LOGITS
     トート
    0.38
     ܡ
    0.35
     ‬
    0.35
     Malibu
    0.34
     నుండి
    0.34
     Breeders
    0.33
     ダ
    0.33
     rightfully
    0.33
     実
    0.33
     ム
    0.33
    Activations Density 0.001%

    No Known Activations