© 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. 103353
    Prev
    Next
    INDEX
    Explanations

    admitted to the bar

    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
     header
    -0.72
     substitute
    -0.70
     kertoo
    -0.69
     headers
    -0.69
    atás
    -0.68
     Thackeray
    -0.67
     råd
    -0.67
    dood
    -0.67
    sium
    -0.66
    Ǒ
    -0.66
    POSITIVE LOGITS
    NBA
    0.82
    lismo
    0.79
     riêng
    0.79
     NBA
    0.78
     Qualifying
    0.75
     demi
    0.74
    Solicit
    0.73
    붙
    0.73
    roll
    0.73
    forall
    0.71
    Activations Density 0.016%

    No Known Activations