© 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. 34-GEMMASCOPE-RES-131K
    7. 2860
    Prev
    Next
    INDEX
    Explanations

    object property access

    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
    olybden
    -0.86
    ulong
    -0.84
     Naga
    -0.80
    <'
    -0.75
    THS
    -0.72
    充
    -0.70
     limbo
    -0.70
     mää
    -0.69
    xit
    -0.69
    uat
    -0.69
    POSITIVE LOGITS
     Wetlands
    0.84
    Bekijk
    0.82
     visibilidad
    0.77
    Welke
    0.74
    ánicos
    0.74
     добавить
    0.73
    IsPostBack
    0.73
    灑
    0.73
    typal
    0.72
     visibility
    0.71
    Activations Density 0.015%

    No Known Activations