© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65979
    Prev
    Next
    INDEX
    Explanations

    windshield wipers

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

    The neuron is detecting mentions of automotive glass components—especially windshields and related window/glass parts.

    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
     about
    -1.63
    settes
    -1.30
    ங
    -1.30
    Noe
    -1.29
    ulpt
    -1.29
    umacher
    -1.28
     melindungi
    -1.27
     aparición
    -1.27
    Attributed
    -1.25
    tazione
    -1.23
    POSITIVE LOGITS
    菒
    1.68
     of
    1.40
    nargs
    1.38
    ICIENCY
    1.34
     we
    1.34
    ＊＊＊
    1.33
    买卖
    1.32
     glass
    1.32
    售价
    1.30
     стиля
    1.27
    Activations Density 0.055%

    No Known Activations