© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2757
    Prev
    Next
    INDEX
    Explanations

    Category

    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
     in
    -2.14
     at
    -1.62
     on
    -1.56
     or
    -1.42
     (
    -1.38
     not
    -1.36
     all
    -1.34
    いただけます
    -1.31
     as
    -1.25
     had
    -1.25
    POSITIVE LOGITS
    <h3>
    1.50
    <h2>
    1.43
     alcune
    1.38
     molte
    1.33
    完成です
    1.32
     alcuni
    1.27
    なども
    1.26
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.25
     băr
    1.25
     magnific
    1.24
    Activations Density 0.022%

    No Known Activations