© 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. 8409
    Prev
    Next
    INDEX
    Explanations

    daily frequencies

    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
     clutter
    -1.41
    犼
    -1.38
    quatre
    -1.38
    自然是
    -1.34
    神の
    -1.34
    divarius
    -1.34
     prič
    -1.34
     trzec
    -1.34
    ciutto
    -1.33
     &
    -1.30
    POSITIVE LOGITS
    (´
    1.50
     using
    1.50
     during
    1.43
     for
    1.41
    including
    1.41
     spesies
    1.36
     tersenyum
    1.35
    (*´
    1.33
     with
    1.33
     in
    1.33
    Activations Density 0.056%

    No Known Activations