© 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. 33767
    Prev
    Next
    INDEX
    Explanations

    shootings and mosques

    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
     school
    -0.94
    volatile
    -0.81
    ਦੇ
    -0.78
     School
    -0.77
     puddle
    -0.75
    indeer
    -0.75
    氏は
    -0.74
     dici
    -0.74
    済み
    -0.72
     teaches
    -0.71
    POSITIVE LOGITS
     Christchurch
    1.02
     manifesto
    0.95
    getA
    0.91
    ОВ
    0.81
     manif
    0.81
     gunman
    0.78
     boomer
    0.77
    Brent
    0.75
    ęg
    0.75
     δο
    0.73
    Activations Density 0.014%

    No Known Activations