© 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. 13403
    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
    ваме
    -1.11
    𝛾
    -1.08
     més
    -1.01
     mors
    -1.01
     opsi
    -1.00
    gave
    -0.99
     tuin
    -0.98
    ENT
    -0.98
    enderita
    -0.98
    hows
    -0.98
    POSITIVE LOGITS
    phée
    1.24
    Although
    1.17
    Sometimes
    1.13
    」，
    1.10
    Though
    1.09
    While
    1.09
     to
    1.07
    Perhaps
    1.07
    </h3>
    1.05
    Often
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.