© 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. 1267
    Prev
    Next
    INDEX
    Explanations

    one followed by a noun

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

    The neuron flags occurrences of the word “one,” especially when it’s used to introduce or enumerate an example.

    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
    ش
    0.85
     Beginn
    0.80
    دين
    0.79
    ने
    0.77
     néhány
    0.77
     locaux
    0.76
     самые
    0.74
    内容は
    0.73
    }
    0.71
    ය
    0.71
    POSITIVE LOGITS
     hundred
    0.96
    ida
    0.83
    াকী
    0.80
    hundred
    0.71
     wonders
    0.70
    fifth
    0.69
    ைட்
    0.69
    єї
    0.66
    যোগে
    0.66
     vehemently
    0.66
    Activations Density 0.130%

    No Known Activations