© 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. 129313
    Prev
    Next
    INDEX
    Explanations

    tokens after punctuation

    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
    lecteur
    -1.03
    %).
    -1.02
     our
    -1.02
     skon
    -0.98
     OUR
    -0.98
    anggap
    -0.98
     stanovnika
    -0.98
     mód
    -0.97
     some
    -0.96
    Songs
    -0.94
    POSITIVE LOGITS
    Publié
    1.14
     gover
    1.09
    Jeudi
    1.05
     heutige
    1.05
    但是在
    1.01
     quadrat
    0.97
     estudos
    0.96
    难怪
    0.96
    künfte
    0.95
    Searched
    0.95
    Activations Density 0.012%

    No Known Activations