© 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. 85225
    Prev
    Next
    INDEX
    Explanations

    видео, ife, Como

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

    This neuron detects the German question word “wie” (in any casing).

    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
    ),
    -3.53
    ).
    -3.41
    ",
    -3.05
    t
    -2.97
    A
    -2.91
    U
    -2.89
    "
    -2.72
    ."
    -2.67
     \
    -2.59
     gewisser
    -2.58
    POSITIVE LOGITS
    ίες
    2.97
    鲠
    2.83
    were
    2.80
     mélang
    2.69
    嘥
    2.64
    s
    2.61
    ть
    2.58
     étaient
    2.56
     tinham
    2.48
    筇
    2.48
    Activations Density 0.001%

    No Known Activations