© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10318
    Prev
    Next
    INDEX
    Explanations

    mindfulness and Buddhist frameworks

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

    The neuron fires on numeric values and measurement/specification 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_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
     ialah
    0.75
     ise
    0.69
     είναι
    0.68
     eine
    0.67
     essendo
    0.66
     maka
    0.65
     zunächst
    0.65
     :,
    0.65
     nahin
    0.64
     ស
    0.63
    POSITIVE LOGITS
    etc
    0.86
    Other
    0.80
    Otros
    0.77
    <h3>
    0.74
    <h2>
    0.71
    <h1>
    0.70
    <h5>
    0.68
    Примеча
    0.68
    <blockquote>
    0.67
    Note
    0.66
    Activations Density 0.153%

    No Known Activations