© 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. 1488
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of fish species names.

    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
    芏
    0.83
    ্ডিং
    0.75
    ໄດ້
    0.74
     শতাংশ
    0.74
    გი
    0.72
     vacancies
    0.71
     tuổi
    0.71
     scru
    0.71
    뗑
    0.71
    ನ್ನೂ
    0.70
    POSITIVE LOGITS
    ال
    0.84
    ع
    0.82
    ن
    0.80
     ange
    0.75
     バー
    0.74
     آرام
    0.73
     مجال
    0.69
    Ｘ
    0.69
     ابن
    0.68
    xan
    0.68
    Activations Density 0.001%

    No Known Activations