© 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. 100586
    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
     auttaa
    -1.00
     tremend
    -1.00
     annihilated
    -0.91
     ajustable
    -0.86
    hyth
    -0.86
     periphery
    -0.85
    nachron
    -0.85
    geddon
    -0.84
     nativo
    -0.84
    ыре
    -0.84
    POSITIVE LOGITS
     and
    1.20
     Так
    1.09
     druh
    1.03
     energía
    1.02
    UnitPrice
    0.97
    Aihe
    0.96
     На
    0.95
     Zhang
    0.91
     Ма
    0.89
    ksam
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.