© 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. 65307
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    The neuron activates on numeric literals (including integers and decimal numbers) 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
     „
    -0.94
     περισσότε
    -0.90
     also
    -0.86
    um
    -0.85
    in
    -0.84
    ton
    -0.81
     DA
    -0.79
    不该
    -0.79
     Sparse
    -0.79
    保育園
    -0.77
    POSITIVE LOGITS
     cambiado
    0.93
     pascua
    0.88
    Artisan
    0.87
    tisgarh
    0.86
    QSize
    0.85
    wachen
    0.84
    PositiveButton
    0.84
    Durata
    0.84
     Chriftian
    0.84
    فيذ
    0.83
    Activations Density 0.010%

    No Known Activations