© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    commands, structure, lists, and code

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

    This neuron primarily detects numeric values with decimal points (floating-point numbers).

    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_24_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
     map
    0.40
     ­
    0.39
     students
    0.36
     step
    0.36
     sufficient
    0.36
     information
    0.35
      
    0.35
     steps
    0.35
     service
    0.34
     deutsch
    0.34
    POSITIVE LOGITS
     Perkenalkan
    0.45
     Chromatography
    0.43
     Верх
    0.43
     Акаде
    0.42
     <!--<
    0.42
     Ayrıca
    0.41
     Mình
    0.41
     Они
    0.41
     Collagen
    0.41
    ྀ
    0.41
    Activations Density 0.000%

    No Known Activations