© 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. 10055
    Prev
    Next
    INDEX
    Explanations

    names of people and projects

    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
     the
    -3.28
    {
    -3.11
    沨
    -3.06
    ),
    -2.89
    ',
    -2.70
    ﹑
    -2.66
    ،
    -2.61
    \"
    -2.56
     необходимые
    -2.56
    ",
    -2.47
    POSITIVE LOGITS
    uſe
    2.61
    
    2.56
    s
    2.56
    r
    2.53
     применя
    2.53
    on
    2.52
    u
    2.50
    焄
    2.47
    ing
    2.38
    jnych
    2.28
    Activations Density 0.028%

    No Known Activations