© 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. 83288
    Prev
    Next
    INDEX
    Explanations

    precipitation

    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
    чни
    -0.71
    COX
    -0.71
     unimportant
    -0.71
     Nevertheless
    -0.69
     nevertheless
    -0.69
     keines
    -0.68
    amata
    -0.68
    UAV
    -0.68
     Murad
    -0.67
    Боль
    -0.67
    POSITIVE LOGITS
     precipitation
    3.27
     precipitated
    2.77
     Precipitation
    2.70
     precipitate
    2.61
    precip
    2.55
     precipit
    2.53
    Precipitation
    2.44
     precip
    2.39
     precipitates
    2.33
     précip
    1.95
    Activations Density 0.077%

    No Known Activations