© 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. 101189
    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
     frambo
    -1.52
     gena
    -1.38
    If
    -1.36
    <h3>
    -1.32
     produc
    -1.31
     isra
    -1.30
     любой
    -1.30
     Jérusalem
    -1.29
     gesund
    -1.28
    Már
    -1.27
    POSITIVE LOGITS
     and
    1.98
    汌
    1.85
     I
    1.83
     estrecha
    1.56
     respectivos
    1.52
     recopila
    1.48
    ႐
    1.43
    龉
    1.42
    ุทธ
    1.41
     budete
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.