© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    literal or explanatory translations

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

    The neuron detects non‐Latin character sequences, especially Chinese (and other CJK) script tokens.

    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
     entrée
    0.64
     recommend
    0.61
     spender
    0.59
     europea
    0.57
     outperformed
    0.57
    ᱲ
    0.57
     grafica
    0.57
     compete
    0.56
     bens
    0.55
     competes
    0.55
    POSITIVE LOGITS
     พวก
    0.61
     /ˈ
    0.58
    roughly
    0.57
     구
    0.56
     Roughly
    0.56
    literally
    0.55
     The
    0.55
    hereinafter
    0.55
     Here
    0.54
     例文帳に追加
    0.54
    Activations Density 0.019%

    No Known Activations