© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75879
    Prev
    Next
    INDEX
    Explanations

    code segments and configurations

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

    The neuron fires on tokens written in all uppercase—i.e. fully capitalized keywords, acronyms, or constants in code and legal/license text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    она
    -0.73
    勺
    -0.71
     Principal
    -0.71
     tav
    -0.68
     Range
    -0.68
    学年
    -0.67
     cart
    -0.66
     Borne
    -0.65
    gain
    -0.64
    on
    -0.63
    POSITIVE LOGITS
     เหล
    0.73
    sə
    0.72
    atalos
    0.71
    ivor
    0.69
    Dia
    0.69
    thora
    0.68
    datat
    0.68
     Alco
    0.68
     Sotto
    0.67
     intenciones
    0.67
    Activations Density 0.063%

    No Known Activations