© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8194
    Prev
    Next
    INDEX
    Explanations

    how to

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

    This neuron detects list‐item markers—specifically the numeric bullets (e.g. “1.”) that introduce numbered list entries.

    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
    lah
    0.75
    larda
    0.73
    俩
    0.72
    兩種
    0.71
    का
    0.70
    นี่
    0.69
    א
    0.69
    টো
    0.68
    larında
    0.68
    াত্য
    0.68
    POSITIVE LOGITS
     ܡ
    0.71
     ㅁ
    0.68
    ️⃣
    0.67
     Intl
    0.66
     Oscillator
    0.64
     gcc
    0.63
     Depreciation
    0.63
     Shooter
    0.62
     nyc
    0.61
    ⃣
    0.61
    Activations Density 0.007%

    No Known Activations