© 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. 83079
    Prev
    Next
    INDEX
    Explanations

    DF abbreviations and initials

    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
    Mvh
    -0.80
     sweatpants
    -0.78
     Confidential
    -0.74
     Conquest
    -0.73
     przec
    -0.73
     localização
    -0.72
     Quarry
    -0.72
     chairperson
    -0.72
     manutenção
    -0.72
     Cres
    -0.71
    POSITIVE LOGITS
     DF
    1.21
    df
    1.05
     df
    1.00
    DF
    0.90
    姿
    0.85
    ulted
    0.80
     Df
    0.79
    DoubleQuotes
    0.79
    ULTS
    0.76
     civilians
    0.76
    Activations Density 0.021%

    No Known Activations