© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104270
    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
     Oberfläche
    -1.00
     DbType
    -0.96
    iotensin
    -0.95
     a
    -0.94
     kém
    -0.91
     ainda
    -0.91
    -
    -0.91
     SqlDbType
    -0.90
     ancora
    -0.89
     still
    -0.89
    POSITIVE LOGITS
     continuer
    1.10
     asma
    1.09
     bambu
    1.09
     vernac
    1.04
     traged
    1.03
     maillot
    1.03
    kste
    1.02
     durer
    1.02
     pompa
    1.02
     rivi
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.