© 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. 6279
    Prev
    Next
    INDEX
    Explanations

    housing, ship, perched, structural

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

    The neuron detects attribution or “by” credit lines (e.g. “Produced by,” “Powered by,” “Recorded by,” “Designed by,” etc.).

    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
    Massage
    0.91
    Y
    0.91
     VARCHAR
    0.84
    Weapon
    0.84
    Golem
    0.84
     Вы
    0.80
    Sqrt
    0.80
     Mous
    0.78
     restre
    0.77
     Дэ
    0.77
    POSITIVE LOGITS
    弈
    0.72
    レン
    0.71
     प्रतिनिधियों
    0.70
     unsubstituted
    0.68
    原因
    0.68
    ことで
    0.66
    レイン
    0.66
     viewership
    0.65
     reflectors
    0.65
    يذ
    0.64
    Activations Density 0.000%

    No Known Activations