© 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. 14631
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

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

    The neuron detects reporting‐speech attributions—i.e. occurrences of verbs like “said,” “says,” or “told” that introduce or follow quoted statements.

    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
    んですよね
    0.89
     comune
    0.77
     Placeholder
    0.75
    ++++++++++++++++
    0.74
    flashdata
    0.74
     absoluto
    0.72
    dari
    0.72
     captcha
    0.71
     fantasy
    0.70
     spontaneity
    0.70
    POSITIVE LOGITS
    ोटा
    0.81
    \;
    0.77
    र्यंत
    0.75
    \:
    0.72
    \,\
    0.71
     केंद
    0.71
    지만
    0.71
     meliputi
    0.70
     ст
    0.69
    사
    0.69
    Activations Density 0.001%

    No Known Activations