© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86214
    Prev
    Next
    INDEX
    Explanations

    "So," then a word

    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
    ‫‪
    -1.55
    杮
    -1.53
     ceramica
    -1.53
     confé
    -1.52
    型的
    -1.48
     belakang
    -1.47
    УДК
    -1.47
     cenar
    -1.47
    ранее
    -1.46
    」,
    -1.45
    POSITIVE LOGITS
     what
    1.84
     about
    1.80
    <
    1.62
    %
    1.42
    zieć
    1.38
    D
    1.38
    有所
    1.35
    A
    1.35
    a
    1.34
    G
    1.34
    Activations Density 0.010%

    No Known Activations