© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6603
    Prev
    Next
    INDEX
    Explanations

    list items and punctuation

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

    The neuron fires on the section‐heading token “Description.”

    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_31_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
    撰
    0.63
    menos
    0.59
     했던
    0.57
    ācijas
    0.57
    ⌔
    0.57
    >\<^
    0.56
    сэн
    0.55
    Conceptual
    0.55
    STATEMENT
    0.55
    舝
    0.55
    POSITIVE LOGITS
     niece
    0.63
     रे
    0.58
     Ville
    0.58
     super
    0.57
     Uncle
    0.57
     Aunt
    0.57
     nephew
    0.56
     सबकुछ
    0.55
     rental
    0.55
     clothing
    0.54
    Activations Density 0.000%

    No Known Activations