© 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. 7629
    Prev
    Next
    INDEX
    Explanations

    sequence and consequence

    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
    ностью
    -1.45
     noteworthy
    -1.42
     new
    -1.39
    igshid
    -1.38
     There
    -1.37
     their
    -1.34
    </code>
    -1.34
     unusual
    -1.34
     glyphicon
    -1.34
    !("
    -1.33
    POSITIVE LOGITS
     then
    3.08
     потім
    1.93
     therefore
    1.57
     thereafter
    1.56
     thus
    1.49
     thereby
    1.46
     kemudian
    1.42
     Quindi
    1.39
    then
    1.37
     Così
    1.34
    Activations Density 0.224%

    No Known Activations