© 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. 25733
    Prev
    Next
    INDEX
    Explanations

    detailed study or description

    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
    حدى
    -0.89
    criminate
    -0.81
     sodass
    -0.80
    joso
    -0.77
     luckily
    -0.76
    ⌣
    -0.75
    aménagement
    -0.74
     occasionally
    -0.74
    UserList
    -0.73
     trên
    -0.73
    POSITIVE LOGITS
     detailed
    2.81
     подробно
    2.77
     detail
    2.53
     in
    2.36
     дета
    2.27
    Detailed
    2.20
    详细
    2.19
     Detailed
    2.16
    detailed
    2.16
    detail
    2.06
    Activations Density 0.106%

    No Known Activations