© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10330
    Prev
    Next
    INDEX
    Explanations

    SQL data types

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

    The neuron activates on numeric literals—especially floating‐point values and other numbers embedded in URLs, file paths, or performance metrics.

    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
    FormControl
    0.61
     hashCode
    0.58
    isNull
    0.58
    WARN
    0.57
    HttpMessage
    0.55
     }>
    0.54
     Legislature
    0.54
    phoneNumber
    0.53
     Sabrina
    0.52
    PropertyValue
    0.51
    POSITIVE LOGITS
     medium
    0.82
    medium
    0.77
    MEDIUM
    0.70
    Medium
    0.68
     MEDIUM
    0.68
     Medium
    0.67
    祅
    0.62
    याच्या
    0.60
     polypes
    0.59
     मीडियम
    0.59
    Activations Density 0.009%

    No Known Activations