© 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. 8426
    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
     rojos
    -0.99
    信念
    -0.98
    温馨
    -0.94
     melahirkan
    -0.94
     kré
    -0.94
     menetapkan
    -0.94
     cifras
    -0.93
     стене
    -0.92
    teaser
    -0.92
    Barrier
    -0.90
    POSITIVE LOGITS
    through
    1.13
    ryk
    0.97
    Individual
    0.93
    ST
    0.93
     tork
    0.93
     アウト
    0.91
    怼
    0.90
     focuses
    0.89
    ERR
    0.89
     piac
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.