© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74512
    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
    ++)
    -0.98
     kanker
    -0.96
     Leurs
    -0.91
    妗
    -0.90
     plongée
    -0.87
    掳
    -0.87
     Gag
    -0.86
    utup
    -0.86
     turist
    -0.86
    cadores
    -0.85
    POSITIVE LOGITS
    1
    1.19
    2
    1.06
    4
    0.91
    3
    0.85
     accept
    0.81
     receptive
    0.81
    decade
    0.81
     we
    0.81
    Arr
    0.80
    нём
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.