© 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. 7426
    Prev
    Next
    INDEX
    Explanations

    programming symbols and structure

    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
    o
    -1.95
     The
    -1.90
     if
    -1.85
    an
    -1.78
    e
    -1.71
     From
    -1.70
     stately
    -1.63
    a
    -1.59
    ka
    -1.58
    q
    -1.55
    POSITIVE LOGITS
     automóviles
    1.78
     numerosos
    1.78
     verdaderos
    1.76
     zobac
    1.75
    hatch
    1.71
    ↵↵
    1.71
     productores
    1.70
     spezielle
    1.68
     einzelne
    1.67
    initializeApp
    1.67
    Activations Density 0.001%

    No Known Activations