© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9008
    Prev
    Next
    INDEX
    Explanations

    end of names of organizations or events

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

    The neuron activates on apostrophe characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .
    -2.72
    One
    -1.83
     étan
    -1.81
     égard
    -1.74
    них
    -1.71
     Konzentration
    -1.67
     unangemessene
    -1.65
    摇了
    -1.65
    Who
    -1.63
    bamos
    -1.62
    POSITIVE LOGITS
     to
    2.31
     for
    2.17
     quindi
    1.89
     They
    1.73
    </u>
    1.63
    difice
    1.63
    rugada
    1.63
    
    1.61
     nejsou
    1.60
     they
    1.59
    Activations Density 0.013%

    No Known Activations