© 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. 20889
    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
     of
    -1.12
    垸
    -1.05
     sentimiento
    -1.05
    颯
    -1.02
     """
    -1.02
     Objetivos
    -1.00
    кнул
    -0.98
    "—
    -0.97
    trn
    -0.96
     majeur
    -0.96
    POSITIVE LOGITS
    怎样的
    1.08
    以免
    1.07
     indescri
    1.03
    ズレ
    1.02
    袄
    0.96
    无需
    0.96
     paroi
    0.95
     aislados
    0.94
    痿
    0.94
    腘
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.