© 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. 129074
    Prev
    Next
    INDEX
    Explanations

    sharing information

    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
     &
    -1.52
    ਲ਼
    -1.41
     argument
    -1.39
     flesta
    -1.39
     o
    -1.39
    le
    -1.38
     es
    -1.36
     ft
    -1.34
    ↵
    -1.33
    した場合
    -1.33
    POSITIVE LOGITS
     about
    2.13
     anhänger
    1.72
     with
    1.70
    кроссовки
    1.66
    嗐
    1.66
     wich
    1.59
     their
    1.59
     that
    1.59
     事例
    1.59
     how
    1.55
    Activations Density 0.016%

    No Known Activations