© 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. 44281
    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
     makes
    -0.87
    agement
    -0.87
     prevents
    -0.85
    퉁
    -0.85
     encompasses
    -0.84
    似的
    -0.84
     took
    -0.81
    山西
    -0.81
    pairing
    -0.81
    诘
    -0.81
    POSITIVE LOGITS
    の上に
    1.01
    Leider
    0.98
    درب
    0.95
    úť
    0.94
    Ende
    0.94
    Breite
    0.93
     เรา
    0.93
    Nichts
    0.92
    Nein
    0.92
     jusqu
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.