© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    punctuation and finality

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

    The neuron detects mentions of specific brand names or other prominent proper nouns.

    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
    。（
    1.19
     （
    1.16
     (
    1.12
    .(
    1.04
    （
    0.92
    ！（
    0.87
    .
    0.84
    .。
    0.82
     ((
    0.82
    。(
    0.82
    POSITIVE LOGITS
    ),
    1.92
    )،
    1.77
    !),
    1.75
    !)
    1.69
    ?),
    1.66
    )
    1.63
    !!)
    1.58
    ）,
    1.54
    ！)
    1.52
    )、
    1.48
    Activations Density 2.157%

    No Known Activations