© 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. 128648
    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
    structor
    -1.30
    ateľ
    -1.29
     AQUÍ
    -1.27
     zbo
    -1.25
     zwykle
    -1.24
    嫑
    -1.24
    heira
    -1.21
    PostMapping
    -1.20
     Hentet
    -1.17
    ientras
    -1.16
    POSITIVE LOGITS
     was
    1.50
    e
    1.23
     joins
    1.05
     république
    1.04
    is
    1.03
     I
    1.02
     elas
    1.02
    ↵↵
    1.02
    </h2>
    1.02
    ↵
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.