© 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. 7301
    Prev
    Next
    INDEX
    Explanations

    Staff Engineers, Logistic Regression, Emperor Penguins

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

    The neuron fires on proper names, titles, and other significant capitalized or domain-specific terms.

    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
    keletal
    0.80
    ጠቀ
    0.70
    loci
    0.66
    édération
    0.65
    pyr
    0.65
    鱻
    0.65
    Instit
    0.64
    óticos
    0.64
    uyeron
    0.64
    髓
    0.64
    POSITIVE LOGITS
     valamint
    0.83
     alleen
    0.77
     ataupun
    0.71
     sebagai
    0.71
     surroundings
    0.70
     custos
    0.69
     serão
    0.68
     hanya
    0.68
     tetap
    0.68
     dû
    0.68
    Activations Density 1.317%

    No Known Activations