© 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. 22-GEMMASCOPE-RES-131K
    7. 129023
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ناع
    -1.17
     Serviço
    -1.13
    masti
    -1.11
    več
    -1.09
     routinely
    -1.05
     Verkäufer
    -1.01
    nergie
    -1.00
    SizedBox
    -1.00
     chitarra
    -1.00
     SEMESTER
    -0.99
    POSITIVE LOGITS
    了一個
    1.13
    を増
    1.05
    といった
    1.05
     hochwertige
    1.04
    Ejemplos
    1.03
    というのも
    1.01
    がありますが
    1.01
     komplette
    0.98
    达到了
    0.98
    これも
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.