© 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. 8721
    Prev
    Next
    INDEX
    Explanations

    institutional investors

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

    The neuron primarily activates on numeric tokens—especially numbers and numerical values (including decimal‐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
     justifiable
    0.80
     despot
    0.77
     curv
    0.76
     throne
    0.72
     \%$.
    0.72
     vua
    0.72
     Sociedad
    0.71
    教程
    0.70
     argument
    0.70
     incarnation
    0.69
    POSITIVE LOGITS
    ش
    0.91
    ق
    0.79
    ل
    0.75
    то
    0.73
     வைக்க
    0.73
     Mitch
    0.73
    ல்
    0.72
    刚好
    0.72
     पूरी
    0.72
    theless
    0.71
    Activations Density 0.000%

    No Known Activations