© 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. 12639
    Prev
    Next
    INDEX
    Explanations

    my [possessive pronoun] [noun/adjective]

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

    The neuron fires most strongly on the first content word of a new sentence—especially capitalized topic‐sentence words that open declarative or advisory 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
    l
    1.02
    FO
    0.86
    EN
    0.86
    TeX
    0.84
    ك
    0.81
    TNT
    0.80
    STAND
    0.79
    ine
    0.77
    IM
    0.76
    il
    0.74
    POSITIVE LOGITS
    ны
    0.82
     overruling
    0.81
     прибыли
    0.80
    }$:
    0.78
     Sikk
    0.76
    කි
    0.74
     esi
    0.74
    সম্যান
    0.74
     несо
    0.74
    。<
    0.73
    Activations Density 0.001%

    No Known Activations