© 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. 10-GEMMASCOPE-RES-131K
    7. 86695
    Prev
    Next
    INDEX
    Explanations

    highest order, purest form, essential action

    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
     in
    -1.69
     to
    -1.39
     on
    -1.38
    的情况
    -1.20
     by
    -1.19
     have
    -1.16
     ferdig
    -1.14
     leone
    -1.13
     through
    -1.13
    的情况下
    -1.13
    POSITIVE LOGITS
     estime
    1.36
     Estoy
    1.31
    DeclareMath
    1.30
    薮
    1.29
    倏
    1.28
     essas
    1.27
    撂
    1.27
     Información
    1.27
     vraiment
    1.27
     Accesorios
    1.24
    Activations Density 0.020%

    No Known Activations