© 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. 68721
    Prev
    Next
    INDEX
    Explanations

    file paths and commands

    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
     Volkes
    -1.04
     upang
    -0.99
    dant
    -0.96
    Składniki
    -0.94
    )}]{
    -0.92
     Ślą
    -0.90
    žití
    -0.90
    lanca
    -0.88
     життя
    -0.88
    נחנו
    -0.88
    POSITIVE LOGITS
     into
    1.83
     to
    1.20
     in
    1.15
     onto
    1.11
    ativen
    1.02
    appendTo
    1.01
    amese
    0.95
    你这个
    0.90
    那你
    0.89
     Krankheiten
    0.89
    Activations Density 0.031%

    No Known Activations