© 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. 10-GEMMASCOPE-RES-131K
    7. 43937
    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
    ńcu
    -0.98
    </h1>
    -0.94
    </h3>
    -0.94
    宜蘭
    -0.93
    王爷
    -0.91
    メ
    -0.89
    </strong>
    -0.88
     vanilla
    -0.88
     insertions
    -0.87
     paraíso
    -0.85
    POSITIVE LOGITS
     its
    1.21
     impossibile
    1.20
    のと
    1.01
    ądze
    0.99
     carinho
    0.98
    笵
    0.98
    iis
    0.97
     vem
    0.95
    ulisan
    0.95
    amilya
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.