© 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. 34-GEMMASCOPE-RES-131K
    4. 115793
    Prev
    Next
    INDEX
    Explanations

    code file paths and build artifacts

    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_34/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
     stains
    -0.73
    աբ
    -0.69
    の使い方
    -0.69
     Staining
    -0.68
    annot
    -0.65
     Verhaltens
    -0.64
    Converters
    -0.64
    诨
    -0.62
    coder
    -0.62
    atoria
    -0.61
    POSITIVE LOGITS
    imid
    0.75
    Friction
    0.65
     simmer
    0.65
     castillo
    0.65
     Pine
    0.65
    aye
    0.64
     constater
    0.63
    ్
    0.62
    sumi
    0.61
    preventDefault
    0.61
    Activations Density 0.097%

    No Known Activations