© 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. 26822
    Prev
    Next
    INDEX
    Explanations

    lists, articles, scientific papers

    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
     anyone
    -1.20
     anybody
    -1.01
     dedication
    -0.99
     everyone
    -0.94
    :>
    -0.92
     technically
    -0.89
    後來
    -0.88
     public
    -0.88
     teacher
    -0.88
    Anyone
    -0.88
    POSITIVE LOGITS
    ímos
    1.03
    kül
    0.98
    Pho
    0.95
    ıc
    0.94
     arou
    0.94
    Curse
    0.94
     trám
    0.91
     verts
    0.87
    Artículo
    0.86
    similar
    0.84
    Activations Density 0.002%

    No Known Activations