© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130711
    Prev
    Next
    INDEX
    Explanations

    Introduction section headings

    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_10/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
    vignon
    -1.40
    zegovina
    -1.36
     цвят
    -1.33
     Він
    -1.32
    lossary
    -1.31
     to
    -1.28
    ianto
    -1.27
     meistens
    -1.23
    mitas
    -1.21
    thello
    -1.20
    POSITIVE LOGITS
    无论
    1.57
    从
    1.35
    Two
    1.34
     szczeg
    1.34
    Three
    1.33
     даже
    1.32
     variadas
    1.30
    以前
    1.30
     incluso
    1.30
    Five
    1.30
    Activations Density 0.107%

    No Known Activations