© 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. 100414
    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
    astify
    -0.93
    шла
    -0.91
     modulo
    -0.88
    usos
    -0.85
    vitt
    -0.84
    GetLength
    -0.82
    奸
    -0.81
     say
    -0.80
    Lma
    -0.80
     give
    -0.79
    POSITIVE LOGITS
    討論
    1.06
    很容易
    0.91
     turma
    0.90
    INSON
    0.87
    ynka
    0.86
     assuredly
    0.85
    יוחד
    0.85
     Cavalier
    0.84
     earnestly
    0.84
     piling
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.