© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78060
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames or titles

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

    The neuron strongly activates on capitalized tokens that are parts of proper names—people, places, or institutions.

    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
    нятие
    -0.84
    
    -0.80
    ご予約
    -0.80
    Kont
    -0.79
     två
    -0.78
     Mitgliedern
    -0.75
    蘇
    -0.75
     Пра
    -0.75
     månader
    -0.74
     Александра
    -0.73
    POSITIVE LOGITS
     Memorial
    0.99
    Memorial
    0.99
     memorial
    0.96
     MEMORIAL
    0.88
    adins
    0.88
     anderem
    0.85
     terbaik
    0.85
    &=
    0.85
    raus
    0.85
     &=
    0.84
    Activations Density 0.037%

    No Known Activations