© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9301
    Prev
    Next
    INDEX
    Explanations

    categories and their values

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

    The neuron activates on product specification headings (e.g. “Size,” “Dimension,” “Specifications,” “Measurements,” etc.).

    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
     aceptas
    0.69
     $+$
    0.68
     $+\
    0.67
     <--
    0.61
    +$
    0.60
     plus
    0.59
     ଓ
    0.59
    ↵↵↵↵↵↵
    0.59
     ←
    0.58
     aata
    0.58
    POSITIVE LOGITS
    approx
    0.67
    app
    0.58
    約
    0.57
    errorCode
    0.56
    categoria
    0.55
    mainWindow
    0.55
    〓
    0.55
     तकरीबन
    0.55
    direccion
    0.55
    ieres
    0.54
    Activations Density 0.058%

    No Known Activations