© 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. 65480
    Prev
    Next
    INDEX
    Explanations

    test

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

    This neuron activates on the lowercase word “test” (e.g. in filenames, variable names, email addresses, 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
     
    -2.44
    絝
    -2.31
    转头
    -2.22
     や
    -2.11
     '
    -2.09
     When
    -2.09
    från
    -2.06
    AN
    -2.05
     ``
    -2.05
    Ｔ
    -1.98
    POSITIVE LOGITS
    al
    2.56
    es
    2.55
     and
    2.41
     itſelf
    2.41
    er
    2.39
    斯特
    2.34
    ))$_
    2.33
     diza
    2.31
     暮らし
    2.25
    ar
    2.23
    Activations Density 0.011%

    No Known Activations