© 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. 68281
    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
     which
    -2.00
     There
    -1.88
     If
    -1.82
    c
    -1.80
     Although
    -1.77
     showed
    -1.74
     their
    -1.68
     When
    -1.66
     provides
    -1.66
     indicates
    -1.64
    POSITIVE LOGITS
    alakip
    2.14
    also
    2.05
    </i>
    2.02
     delightfully
    2.00
     lauded
    1.99
     renowned
    1.95
     geweldige
    1.91
     prachtige
    1.91
    roughly
    1.91
     strikingly
    1.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.