© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    The neuron flags unusually rare or low-frequency tokens (i.e. uncommon words and abbreviations).

    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
     GoName
    0.86
    oshape
    0.79
     ディ
    0.76
    //
    0.75
     الرياض
    0.73
    urés
    0.72
    いです
    0.72
    oyam
    0.71
     சட்ட
    0.70
     Jwt
    0.70
    POSITIVE LOGITS
    мыш
    0.82
    푀
    0.80
     sle
    0.74
     eerst
    0.73
     варианты
    0.73
    ไม
    0.69
     slee
    0.68
     oude
    0.68
    Золо
    0.68
     нь
    0.67
    Activations Density 0.000%

    No Known Activations