© 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. 22-GEMMASCOPE-RES-131K
    7. 65134
    Prev
    Next
    INDEX
    Explanations

    life events or endings

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

    The neuron fires on numeric literals (numbers and number-like tokens) in the 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_22/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
    asının
    -1.03
    asına
    -1.02
    héro
    -0.99
    ⒎
    -0.98
    titial
    -0.97
    asında
    -0.94
     eſſ
    -0.93
     gelijk
    -0.92
    Aantal
    -0.91
    você
    -0.90
    POSITIVE LOGITS
     eventually
    1.23
     schließlich
    0.98
     ultimately
    0.98
     G
    0.96
     T
    0.95
     die
    0.94
     P
    0.93
     quit
    0.93
     Eventually
    0.89
     общей
    0.88
    Activations Density 0.006%

    No Known Activations