© 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. 10924
    Prev
    Next
    INDEX
    Explanations

    Dunning-Kruger Effect

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

    This neuron primarily activates on numeric tokens—that is, sequences of digits (including multi-digit numbers and numeric measurements).

    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
    ›
    0.71
    <b>
    0.69
    ~
    0.67
    ¥
    0.64
    以下
    0.64
    🖤
    0.63
    他们
    0.62
    DM
    0.62
     mengunjungi
    0.62
    Γ
    0.61
    POSITIVE LOGITS
    ément
    0.75
    ляция
    0.73
    ನ್ಸ್
    0.69
    емым
    0.69
    ঠোর
    0.69
    gerät
    0.68
     colloid
    0.68
    urde
    0.68
     রাখুন
    0.68
     marinade
    0.66
    Activations Density 0.037%

    No Known Activations