© 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. 22-GEMMASCOPE-RES-131K
    7. 25606
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.24
     кури
    -0.94
    boldmath
    -0.91
    licitations
    -0.83
    чения
    -0.82
     trì
    -0.81
    kovsky
    -0.81
    copic
    -0.80
     escaleras
    -0.80
    nsis
    -0.79
    POSITIVE LOGITS
     világ
    0.96
    ządz
    0.89
    ص
    0.88
    >=</
    0.86
    یک
    0.85
    acak
    0.85
    unter
    0.85
    Durante
    0.83
     appelé
    0.83
    žno
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.