© 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. 42338
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation

    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
    7
    -2.45
    5
    -2.44
    6
    -2.42
    4
    -2.33
    .‏
    -2.09
    1
    -2.02
     elétrico
    -2.00
    2
    -1.99
     dibanding
    -1.97
     Organisateur
    -1.96
    POSITIVE LOGITS
     &
    1.88
     of
    1.82
     is
    1.75
    请输入
    1.74
    yeah
    1.68
    🫱
    1.66
     Now
    1.64
    のように
    1.63
    derdag
    1.62
    B
    1.59
    Activations Density 0.028%

    No Known Activations