© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41374
    Prev
    Next
    INDEX
    Explanations

    stere words

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

    The neuron detects occurrences of the “stere-” prefix in words (e.g. stereoscopic, stereospecific, stereophotogrammetry, etc.).

    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
     This
    -3.19
     The
    -2.72
     With
    -2.63
     As
    -2.61
    м
    -2.58
     These
    -2.56
     If
    -2.55
     For
    -2.55
     Instead
    -2.53
     During
    -2.52
    POSITIVE LOGITS
    久し
    2.70
    　＊
    2.52
     hochwer
    2.36
     limitado
    2.34
    翃
    2.33
    脔
    2.33
    詳しくは
    2.31
     Geräten
    2.31
    ・・・・・
    2.22
    珢
    2.22
    Activations Density 0.017%

    No Known Activations