© 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. 65167
    Prev
    Next
    INDEX
    Explanations

    document starts/code includes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    麃
    -1.04
     kado
    -1.01
     lavabo
    -1.01
    ции
    -1.00
    tyimages
    -0.98
     fuir
    -0.96
     meub
    -0.95
     conva
    -0.94
    licante
    -0.94
     alternatif
    -0.94
    POSITIVE LOGITS
     again
    1.01
     will
    0.93
    utorial
    0.90
     to
    0.90
     sağlık
    0.86
     fermions
    0.84
     pupa
    0.84
    asilkan
    0.83
     entweder
    0.81
    árqu
    0.81
    Activations Density 0.000%

    No Known Activations