© 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. 4942
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to numeric tokens—especially decimal‐formatted values (like percentages or 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
     accion
    0.84
     alternativa
    0.77
     альтерна
    0.76
     consultar
    0.76
     मालूम
    0.75
    ്
    0.75
     incluir
    0.74
     obstante
    0.73
     intentos
    0.73
     എന്നാൽ
    0.73
    POSITIVE LOGITS
    س
    0.98
    ges
    0.78
    št
    0.77
    🎨
    0.77
    ס
    0.75
    Inside
    0.73
    ✨
    0.73
    🛡
    0.73
     Photoshop
    0.72
    🍪
    0.72
    Activations Density 0.002%

    No Known Activations