© 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. 34137
    Prev
    Next
    INDEX
    Explanations

    web paths and includes

    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
    toDouble
    -1.47
    なのかな
    -1.34
     škoda
    -1.28
     its
    -1.27
     Drž
    -1.23
     podoba
    -1.20
     and
    -1.20
     Popis
    -1.20
     entregas
    -1.20
     jedna
    -1.18
    POSITIVE LOGITS
    ha
    1.42
    で
    1.32
    なので
    1.32
    もちろん
    1.30
    un
    1.30
    ka
    1.28
    o
    1.27
    j
    1.27
    ch
    1.23
    了一个
    1.23
    Activations Density 0.010%

    No Known Activations