© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    dividing into groups, stages, phases

    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
    0
    -0.93
    5
    -0.88
     asemenea
    -0.84
    Collective
    -0.79
     acreditar
    -0.79
     celor
    -0.79
     dnia
    -0.79
    8
    -0.78
    的一部分
    -0.77
     suspensão
    -0.77
    POSITIVE LOGITS
     of
    1.31
    に分
    1.12
    /¯
    1.05
    逡
    1.04
     jugu
    1.02
    лежки
    1.01
    ято
    1.01
    нии
    0.96
    hdysval
    0.96
     masing
    0.96
    Activations Density 0.253%

    No Known Activations