© 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. 7075
    Prev
    Next
    INDEX
    Explanations

    code with specific keywords

    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
     resold
    -0.73
    bdd
    -0.69
     Avocado
    -0.68
    楽部
    -0.68
    WebElement
    -0.66
    ارد
    -0.66
    displaystyle
    -0.66
    demografi
    -0.66
    ("\"
    -0.66
    utschland
    -0.66
    POSITIVE LOGITS
    皂
    0.70
     Boiling
    0.69
    Captured
    0.68
     HIGHLIGHTS
    0.66
     Rounds
    0.66
     TRANSM
    0.65
    RELL
    0.65
     Rouge
    0.65
    fycat
    0.65
     Grá
    0.64
    Activations Density 0.080%

    No Known Activations