© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104738
    Prev
    Next
    INDEX
    Explanations

    `self` or `this` after code syntax

    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
     ARISING
    -1.08
    anglais
    -1.07
    belongs
    -1.06
     telefonu
    -1.05
     kontaktu
    -1.04
     >=",
    -1.02
     freundlich
    -1.02
    푆
    -1.00
     mascota
    -1.00
    cerer
    -0.99
    POSITIVE LOGITS
    ↵↵
    0.99
     on
    0.92
    が
    0.90
    hdas
    0.83
     Although
    0.81
    🤤
    0.80
     R
    0.79
     should
    0.79
     Even
    0.79
    🙋
    0.77
    Activations Density 0.003%

    No Known Activations