© 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. 22-GEMMASCOPE-RES-131K
    7. 130898
    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
     Londra
    -1.06
     deres
    -1.04
     halus
    -1.02
     Molto
    -1.02
    vous
    -0.99
     segu
    -0.98
    reven
    -0.96
     AGRE
    -0.96
     demostr
    -0.95
    [{\
    -0.95
    POSITIVE LOGITS
     and
    1.11
     not
    1.04
    ],
    1.03
     району
    1.02
    tudo
    1.00
     nhung
    0.96
     ['$
    0.94
     sustancias
    0.93
    thwaite
    0.93
     آمریک
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.