© 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. 12400
    Prev
    Next
    INDEX
    Explanations

    plan or curriculum

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find markdown‐style section headings indicated by “##” followed by a numeric identifier.

    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
    ar
    1.45
    ق
    1.44
    ра
    1.37
     DOS
    1.30
    s
    1.29
     niên
    1.26
    tutorial
    1.25
     pretende
    1.25
    est
    1.21
    ের
    1.21
    POSITIVE LOGITS
    Referències
    1.42
    Przypisy
    1.41
    те
    1.39
     비해
    1.33
    ہ
    1.30
    rš
    1.30
    い
    1.30
    𝘪
    1.30
    ло
    1.29
    ză
    1.28
    Activations Density 0.000%

    No Known Activations