© 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. 22-GEMMASCOPE-RES-131K
    7. 93061
    Prev
    Next
    INDEX
    Explanations

    record producer, record deal

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

    The neuron detects occurrences of the word “record” (and its derivatives like “recording”).

    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
    \
    -3.09
     VERY
    -2.53
     музыка
    -2.34
    .'
    -2.28
     /
    -2.27
    Hmmm
    -2.25
     вашу
    -2.25
    4
    -2.23
     在
    -2.23
    熺
    -2.19
    POSITIVE LOGITS
    ”;
    2.88
    欵
    2.78
    縂
    2.77
    ”:
    2.70
    ”，
    2.66
     permitem
    2.66
    ——”
    2.61
     provides
    2.58
    ',
    2.41
    鸯
    2.34
    Activations Density 0.037%

    No Known Activations