© 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. 7376
    Prev
    Next
    INDEX
    Explanations

    Boston

    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
    Ꮀ
    -2.58
    哢
    -2.41
    自然的
    -2.27
     attore
    -2.22
     diki
    -2.19
     světa
    -2.19
     tecnici
    -2.17
     plezier
    -2.17
    違う
    -2.16
     dekoratif
    -2.16
    POSITIVE LOGITS
    .;
    2.66
     {
    2.61
    ."
    2.52
    2
    2.41
    .,
    2.41
    </b>
    2.25
    ./
    2.25
    ’
    2.22
     Eighty
    2.19
    In
    2.17
    Activations Density 0.004%

    No Known Activations