© 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. 86185
    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
     that
    -1.13
    developing
    -1.05
     atractivos
    -1.03
    längerung
    -1.02
     imprescin
    -1.02
     embarazada
    -1.01
    espacio
    -1.00
    ܜ
    -1.00
    kemeja
    -0.99
     ills
    -0.98
    POSITIVE LOGITS
    pano
    1.16
     also
    1.08
     більше
    1.03
    砚
    1.02
    aloe
    0.98
     среднего
    0.96
    addTab
    0.96
    тивы
    0.96
     époque
    0.94
    bustion
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.