© 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. 70115
    Prev
    Next
    INDEX
    Explanations

    modern moral subjects

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

    The neuron strongly activates on numeric tokens (years, dates, volumes, and other numbers).

    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
     Napoleon
    -0.89
     Chopin
    -0.75
     Außer
    -0.73
    Napoleon
    -0.73
    ධ
    -0.71
     Dummies
    -0.71
     upsets
    -0.70
    íu
    -0.69
     Dewan
    -0.69
     Sollte
    -0.68
    POSITIVE LOGITS
     London
    0.79
     Sublime
    0.76
    undial
    0.75
     Addison
    0.75
     Kuchen
    0.75
     парла
    0.74
    نجليز
    0.73
     eighteenth
    0.73
     Subscription
    0.72
    midrule
    0.72
    Activations Density 0.064%

    No Known Activations