© 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. 321
    Prev
    Next
    INDEX
    Explanations

    names like Alice

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

    This neuron activates on capitalized named-entity tokens (proper nouns, person and place names).

    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
     circadian
    -0.90
    ясь
    -0.84
    ząt
    -0.77
    躁
    -0.77
     docile
    -0.76
     Gild
    -0.75
     способ
    -0.75
    หน้า
    -0.74
    ༉
    -0.74
    ůže
    -0.72
    POSITIVE LOGITS
     crítico
    0.76
    loans
    0.76
     Abdu
    0.73
     Anniversary
    0.72
    彫刻
    0.71
     stuck
    0.68
    '>
    0.68
    ered
    0.66
    뻔
    0.66
    wf
    0.64
    Activations Density 0.017%

    No Known Activations