© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6462
    Prev
    Next
    INDEX
    Explanations

    letters or numbers separated by symbols

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

    The neuron fires on numeric tokens containing decimal points (i.e. 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
    的过程
    0.76
    dır
    0.75
    称为
    0.72
     Eing
    0.72
     limitaciones
    0.72
     વડે
    0.71
     cometido
    0.69
    て
    0.69
    ー
    0.68
    ος
    0.68
    POSITIVE LOGITS
     Aisha
    0.80
    el
    0.78
    तम
    0.73
     traumat
    0.72
    elat
    0.72
     nightclub
    0.71
     trauma
    0.70
    กรณ์
    0.70
     گزشتہ
    0.70
     آی
    0.70
    Activations Density 0.001%

    No Known Activations