© 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. 73127
    Prev
    Next
    INDEX
    Explanations

    quotations enclosing specific terms

    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
     establish
    -2.50
     řešení
    -2.48
     emphasize
    -2.47
     soothing
    -2.39
     sonriente
    -2.39
     hermos
    -2.34
     strengthen
    -2.34
     empresas
    -2.34
     comum
    -2.33
     gracios
    -2.33
    POSITIVE LOGITS
     of
    3.06
    '
    2.83
    u
    2.77
    й
    2.66
     faisant
    2.64
    ters
    2.47
    *
    2.45
     we
    2.41
    </strong>
    2.27
    “
    2.22
    Activations Density 0.001%

    No Known Activations