© 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. 103514
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    感じです
    -1.90
    ところに
    -1.88
    感じで
    -1.84
    ⬮
    -1.77
    O
    -1.69
    Abbildung
    -1.62
    譏
    -1.62
    ’
    -1.54
    Зно
    -1.52
    をします
    -1.52
    POSITIVE LOGITS
     (
    1.65
     into
    1.58
     such
    1.55
    一
    1.55
    に
    1.55
    ちなみに
    1.51
     verrez
    1.50
     precisam
    1.46
     ("
    1.45
    метров
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.