© 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. 13530
    Prev
    Next
    INDEX
    Explanations

    explanation or reasoning

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

    The neuron fires on floating‐point numerical values—i.e. decimal measurements (often sizing or dimension figures).

    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
    fetch
    0.62
    Grey
    0.60
    bring
    0.57
    actionMode
    0.55
    
    0.55
    ~
    0.54
    setAttribute
    0.53
    ｐ
    0.53
    iser
    0.53
    Leia
    0.53
    POSITIVE LOGITS
     आंसर
    0.73
    ள்கள்
    0.69
     教え
    0.67
     clonal
    0.66
     ね
    0.64
     ชื่อ
    0.62
     丸
    0.62
     父
    0.61
     สน
    0.61
     plum
    0.61
    Activations Density 0.001%

    No Known Activations