© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99336
    Prev
    Next
    INDEX
    Explanations

    boats and water activities

    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_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
    tabular
    -1.25
    ộm
    -1.20
     فيها
    -1.12
     つけ
    -1.11
     Transmitter
    -1.05
    Транспорт
    -1.05
    Armenia
    -1.02
    zędu
    -1.02
     komunikasi
    -1.02
    er
    -1.02
    POSITIVE LOGITS
     Erkrank
    1.31
     ganhou
    1.20
    ,*
    1.20
    ilización
    1.12
     adalah
    1.10
     negó
    1.09
     lu
    1.09
     že
    1.08
    клар
    1.07
    ,"
    1.05
    Activations Density 0.055%

    No Known Activations