© 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. 22-GEMMASCOPE-RES-131K
    7. 27791
    Prev
    Next
    INDEX
    Explanations

    not to

    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
     gorro
    -0.99
     pantalón
    -0.98
     häl
    -0.95
     matiz
    -0.94
    elding
    -0.94
     our
    -0.92
     cœurs
    -0.90
     savez
    -0.89
     célè
    -0.89
     lourdes
    -0.88
    POSITIVE LOGITS
    任何
    1.02
     any
    0.97
    被
    0.95
    TInt
    0.94
    brook
    0.90
     babys
    0.86
     anything
    0.84
     acquies
    0.84
    接受
    0.82
     herhangi
    0.82
    Activations Density 0.038%

    No Known Activations