© 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. 60491
    Prev
    Next
    INDEX
    Explanations

    source of

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

    The neuron fires on technical mentions of an energy or wave-emitting “source” (e.g. an X-ray source, acoustic source, light source) in patent-style descriptions.

    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
    5
    -2.19
    2
    -2.17
     illustrationer
    -1.96
    4
    -1.95
    //
    -1.82
    6
    -1.81
    3
    -1.80
    7
    -1.75
    花了
    -1.73
     aveo
    -1.73
    POSITIVE LOGITS
     in
    1.79
     to
    1.77
    IQR
    1.65
    XXV
    1.64
     güne
    1.61
     üç
    1.60
     marcado
    1.59
    Ayy
    1.50
     Thus
    1.49
     soll
    1.46
    Activations Density 0.072%

    No Known Activations