© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    JavaScript, Q:, Citybus

    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
    唧
    -0.81
     прине
    -0.79
    alder
    -0.77
    }%
    
    -0.77
     jenner
    -0.77
    roku
    -0.77
     smtplib
    -0.77
     detalhes
    -0.74
    subtract
    -0.73
    Zeneca
    -0.73
    POSITIVE LOGITS
    钥
    0.95
     commencing
    0.90
     revisor
    0.90
     moneys
    0.89
     terrorismo
    0.82
    ƌ
    0.82
     harmonious
    0.80
    HISTORY
    0.80
    绰
    0.79
    HOUSE
    0.79
    Activations Density 0.026%

    No Known Activations