© 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. 5215
    Prev
    Next
    INDEX
    Explanations

    equations or code snippets

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

    The neuron detects numeric tokens representing geographic coordinates (floating‐point latitude/longitude values).

    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
    me
    0.91
    mo
    0.90
    y
    0.87
    mu
    0.86
    liel
    0.85
    s
    0.83
    ar
    0.77
    la
    0.77
     Kavan
    0.76
    lé
    0.75
    POSITIVE LOGITS
    MessageNow
    0.87
    Printing
    0.82
    Salve
    0.81
    Ви
    0.79
    Як
    0.77
    Widget
    0.76
    Framebuffer
    0.76
    бами
    0.75
    Faction
    0.74
    Ж
    0.74
    Activations Density 0.000%

    No Known Activations