© 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. 66129
    Prev
    Next
    INDEX
    Explanations

    air conditioner compressor

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

    The neuron fires on occurrences of the word “conditioner” (as in hair conditioner or air conditioner).

    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
    replyreport
    -2.44
    鶿
    -2.38
    (?)
    -2.38
     To
    -2.34
    𝟮
    -2.31
    “
    -2.25
     periods
    -2.19
     лишь
    -2.14
     pours
    -2.14
     heightened
    -2.09
    POSITIVE LOGITS
    泐
    3.13
    镚
    2.50
     Gästen
    2.38
    蟥
    2.27
    釭
    2.20
    鉏
    2.19
    ventes
    2.16
     need
    2.16
     geda
    2.13
    雠
    2.13
    Activations Density 0.008%

    No Known Activations