© 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. 26601
    Prev
    Next
    INDEX
    Explanations

    imaging and mapping data

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

    The neuron strongly fires on technical terms denoting scientific imaging, mapping, or measurement methods (e.g. “imaging,” “ellipsometry,” “maps,” “matrix”).

    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
    chae
    -0.96
    six
    -0.96
    curve
    -0.93
    斥
    -0.92
    P
    -0.89
     ਅਤੇ
    -0.88
     curve
    -0.88
     tiré
    -0.86
    gaged
    -0.85
     defender
    -0.85
    POSITIVE LOGITS
     maps
    1.33
     map
    1.06
     Maps
    0.93
    map
    0.92
    [:,:,
    0.91
    Maps
    0.91
    Distribu
    0.88
     Carré
    0.86
     resultMap
    0.85
    地圖
    0.85
    Activations Density 0.159%

    No Known Activations