© 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. 6417
    Prev
    Next
    INDEX
    Explanations

    variable, map, mammals, numbers

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

    The neuron responds to mentions of trademarks, registered marks, and related legal or proprietary labeling in text.

    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
     සම
    0.74
    かも
    0.73
    ိမ်
    0.70
    、
    0.69
     жизнь
    0.68
    ﮈ
    0.68
    誕生日
    0.67
    一人
    0.66
     испыта
    0.66
    祝
    0.65
    POSITIVE LOGITS
     primed
    0.71
     fungsi
    0.71
    alities
    0.71
     indispensable
    0.71
     borrowings
    0.70
     imb
    0.69
     getters
    0.67
     ramas
    0.66
     termes
    0.65
     Siles
    0.65
    Activations Density 0.022%

    No Known Activations