© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11101
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a period followed by "As"

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

    The neuron fires on specific named entities or product‐style titles (e.g. proper nouns and catalog/item names).

    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
    ↵↵↵↵↵↵↵
    0.66
    ↵↵↵
    0.63
    <start_of_image>
    0.63
    ↵↵↵↵↵↵
    0.61
    ↵↵↵↵↵
    0.60
     =\
    0.59
    ↵↵↵↵↵↵↵↵↵↵↵
    0.58
    ↵↵↵↵↵↵↵↵↵
    0.57
     ou
    0.56
    ashed
    0.56
    POSITIVE LOGITS
    неопр
    0.59
    BibitemOpen
    0.59
    mux
    0.58
    centralwidget
    0.56
    setcounter
    0.55
    pendown
    0.55
    бил
    0.53
    inplace
    0.53
    addGap
    0.52
    rotating
    0.52
    Activations Density 0.399%

    No Known Activations