© 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. 71538
    Prev
    Next
    INDEX
    Explanations

    Markov chains and models

    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
    ’
    -3.72
    ,
    -3.23
     –
    -3.13
     The
    -2.91
    1
    -2.39
     einfacher
    -2.25
    8
    -2.23
     con
    -2.19
    \
    -2.16
    7
    -2.11
    POSITIVE LOGITS
    愎
    3.14
    婼
    2.88
    呖
    2.86
    zzlement
    2.64
    秾
    2.61
    瓩
    2.50
    殛
    2.48
    鹧
    2.47
    喾
    2.44
    墬
    2.44
    Activations Density 0.005%

    No Known Activations