© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12680
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to tokens in all‐caps (and similar uppercase sequences or codes), such as section headings, product identifiers, and other shouty/title‐style words.

    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_31_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
    ↵
    1.27
    ↵↵↵
    1.23
    ↵↵
    1.15
    ↵↵↵↵
    1.11
    ↵↵↵↵↵↵
    0.97
    ↵↵↵↵↵
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵
    0.92
    ↵↵↵↵↵↵↵↵↵↵
    0.90
     }
    0.89
    POSITIVE LOGITS
    ‌های
    0.56
    ल्लिंग
    0.55
    ভাষায়
    0.52
    ச்சூழ
    0.52
     هایی
    0.51
     यही
    0.51
     sciences
    0.50
    міністра
    0.50
    ‌هایی
    0.50
    ...).
    0.49
    Activations Density 0.015%

    No Known Activations