© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103589
    Prev
    Next
    INDEX
    Explanations

    session getAttribute or context

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

    The neuron fires on numeric tokens (i.e. digits or version/build 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_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
    SURFACE
    -0.75
     Shoulders
    -0.70
    spray
    -0.70
     spraying
    -0.69
    ẩu
    -0.69
    pico
    -0.68
    Spray
    -0.68
     fragmentary
    -0.67
     Spray
    -0.66
     intram
    -0.66
    POSITIVE LOGITS
     attribute
    1.11
    getAttribute
    1.09
    setAttribute
    1.09
    HttpSession
    1.05
     Http
    1.05
    attribute
    1.02
     session
    1.01
    session
    0.92
     Attribute
    0.88
    Attribute
    0.88
    Activations Density 0.010%

    No Known Activations