© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15797
    Prev
    Next
    INDEX
    Explanations

    reliance on, methods of, protection, confrontations

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

    The neuron fires strongly on common short “function” words and conjunctions/prepositions/articles (e.g. “for,” “a,” “or,” “the,” “Co.,” “This,” “transfer,” “partially”).

    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
    läge
    0.98
     collinear
    0.97
     austenitic
    0.91
    ㄿ
    0.91
     filamentous
    0.91
    स्ट
    0.89
     outliers
    0.89
     foreseen
    0.89
     endothelial
    0.89
    লোকের
    0.89
    POSITIVE LOGITS
    a
    0.86
     
    0.80
    razier
    0.76
     viac
    0.75
     אי
    0.74
    ی
    0.73
     ต
    0.71
     “
    0.70
    ה
    0.69
    ig
    0.69
    Activations Density 0.001%

    No Known Activations