© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112434
    Prev
    Next
    INDEX
    Explanations

    中、上、下、内、前、mid (position/direction)

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

    This neuron activates on Chinese-language tokens (i.e. individual Chinese words/characters) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$
    -1.89
    );
    -1.88
    ')
    -1.84
    ');
    -1.76
    ;
    
    -1.70
     and
    -1.69
    🧚
    -1.67
    🌻
    -1.66
    ul
    -1.65
    ❣
    -1.63
    POSITIVE LOGITS
    沒有
    1.88
    acaktır
    1.77
    2
    1.77
    9
    1.74
     paramètres
    1.73
     beneficiario
    1.71
     sonhos
    1.70
     véhicules
    1.69
    都不是
    1.68
    8
    1.68
    Activations Density 0.001%

    No Known Activations