© 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. 5423
    Prev
    Next
    INDEX
    Explanations

    foreign characters

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

    The neuron fires strongly on the very first “content” token that follows a list item or section marker (e.g. after a numbered or bulleted heading), i.e. it detects the start of new list entries or sections.

    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
    te
    0.85
    u
    0.78
    ная
    0.76
    ra
    0.73
    rax
    0.71
     enda
    0.70
    ль
    0.70
     своего
    0.70
     zij
    0.69
     отдела
    0.69
    POSITIVE LOGITS
    Trên
    0.91
    Ş
    0.85
    ച
    0.84
    Ж
    0.82
    Sensitive
    0.80
    ඇ
    0.80
    یو
    0.79
    GES
    0.79
    Từ
    0.79
    UGUST
    0.79
    Activations Density 0.000%

    No Known Activations