© 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. 84356
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     which
    -1.55
     zucchero
    -1.46
     the
    -1.46
     their
    -1.35
    泚
    -1.30
    Rote
    -1.30
    ————————
    -1.23
     snippets
    -1.22
    Relig
    -1.21
    -1.21
    POSITIVE LOGITS
     '
    1.61
    also
    1.55
     vendido
    1.50
     also
    1.49
     atacado
    1.48
    after
    1.41
    鋮
    1.41
    robat
    1.39
    Both
    1.38
    mml
    1.38
    Activations Density 0.052%

    No Known Activations