© 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. 93991
    Prev
    Next
    INDEX
    Explanations

    copyright notices with "Inc."

    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
    град
    -0.85
     Walters
    -0.80
    aktus
    -0.75
    atedral
    -0.74
     Kors
    -0.69
    Ꭲ
    -0.69
    copyright
    -0.69
    phenyl
    -0.68
    ustris
    -0.68
     Maggio
    -0.67
    POSITIVE LOGITS
     أول
    0.71
     Lucre
    0.71
    popd
    0.71
    tocin
    0.70
    報
    0.66
     zaczą
    0.66
     Ана
    0.65
     utafitiHapana
    0.65
    Gruß
    0.64
    ۲۲
    0.64
    Activations Density 0.052%

    No Known Activations