© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    list formatting markers and questions

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

    This neuron detects question sentences by activating strongly on the question‐mark punctuation.

    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
     города
    0.47
     назем
    0.47
    iled
    0.46
     is
    0.46
    깼
    0.45
    യ്‌
    0.45
    няют
    0.44
     হইলেও
    0.44
     কেন্দ্রে
    0.42
    줍니다
    0.42
    POSITIVE LOGITS
    ↵↵
    0.78
     Needless
    0.78
    ↵↵↵
    0.77
    ↵↵↵↵↵
    0.75
     Lastly
    0.75
    ↵↵↵↵
    0.71
     :-)
    0.71
    ↵↵↵↵↵↵
    0.71
     Certainly
    0.70
     Undoubtedly
    0.70
    Activations Density 0.002%

    No Known Activations