© 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. 128813
    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
     acquisto
    -1.16
    simov
    -1.13
     denso
    -1.11
     Provenance
    -1.10
     Mga
    -1.09
    minos
    -1.09
     Uphol
    -1.08
    ्ञ
    -1.06
     Patio
    -1.05
     MCK
    -1.05
    POSITIVE LOGITS
     aquí
    1.23
     -
    1.16
     to
    1.15
     $\
    1.14
    ।
    1.10
    </u>
    1.09
     ("
    1.08
    ING
    1.05
     "
    1.05
     $
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.