© 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. 10-GEMMASCOPE-RES-131K
    7. 85327
    Prev
    Next
    INDEX
    Explanations

    visual examination of conditions

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

    The neuron activates on words and forms related to inspecting or examination (e.g., inspect, inspection, inspecting).

    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
    layah
    -1.41
     Their
    -1.35
     "
    -1.32
     to
    -1.32
     Thus
    -1.29
     Hence
    -1.27
    chloric
    -1.26
    eper
    -1.25
    aratus
    -1.23
    )
    -1.22
    POSITIVE LOGITS
     Mudah
    1.56
     when
    1.48
    Då
    1.47
    Geen
    1.42
    Väl
    1.41
    lampen
    1.40
     maleta
    1.38
     shiny
    1.36
    Продол
    1.35
    افز
    1.34
    Activations Density 0.082%

    No Known Activations