© 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. 34-GEMMASCOPE-RES-131K
    7. 98497
    Prev
    Next
    INDEX
    Explanations

    car wash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     snoring
    -0.89
    自行车
    -0.81
     snare
    -0.81
    guitarra
    -0.78
    โต
    -0.77
     кусо
    -0.76
    harvest
    -0.76
    genic
    -0.75
     الهند
    -0.74
     cramp
    -0.73
    POSITIVE LOGITS
     wash
    2.53
     washing
    2.17
     washes
    2.14
    wash
    2.08
     Wash
    1.98
    Wash
    1.84
    洗
    1.80
     Washing
    1.69
     washed
    1.68
    washing
    1.67
    Activations Density 0.007%

    No Known Activations