© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13321
    Prev
    Next
    INDEX
    Explanations

    lists with parentheses, colons, or bullet points

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

    This neuron detects list-item markers, specifically the asterisk (*) used to denote bullet points.

    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
    ри
    1.32
    很多
    1.32
    ции
    1.27
    রি
    1.22
    )}$,
    1.21
    )}{\
    1.20
    )},\
    1.08
    يد
    1.07
    মূলক
    1.06
    Eq
    1.04
    POSITIVE LOGITS
    א
    1.48
    و
    1.45
    t
    1.44
    ️⃣
    1.43
    ang
    1.42
    ન
    1.38
    து
    1.33
    ことを
    1.27
    ⮚
    1.26
    aj
    1.25
    Activations Density 0.004%

    No Known Activations