© 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. 12432
    Prev
    Next
    INDEX
    Explanations

    wav, vinyl, vaginal, file, wavy

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

    The neuron activates on occurrences of the string “wav” (as in the WAV audio file format).

    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
    ꯹
    -3.22
     イラストレーション
    -3.20
    เกง
    -3.09
    鄚
    -3.06
     valentín
    -2.81
    霂
    -2.73
     兒童
    -2.70
    沄
    -2.66
    ”),
    -2.64
    ”)
    -2.63
    POSITIVE LOGITS
     "
    3.28
     '
    3.14
     
    2.94
    s
    2.94
    ’
    2.83
    '
    2.81
    '"
    2.78
    )
    2.69
     we
    2.64
    眼睛
    2.39
    Activations Density 0.001%

    No Known Activations