© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117902
    Prev
    Next
    INDEX
    Explanations

    newspaper and publication names

    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
     bez
    -0.80
     hornear
    -0.79
    expiry
    -0.76
     comprobar
    -0.76
    uct
    -0.75
     россии
    -0.75
     الأمريكية
    -0.74
    ENABLED
    -0.74
     sposób
    -0.73
     héroes
    -0.73
    POSITIVE LOGITS
     Guardian
    3.03
    Guardian
    2.67
     Telegraph
    2.28
     Times
    2.23
     guardian
    2.14
    guardian
    2.03
    Times
    2.00
     Sunday
    1.95
     GUARD
    1.62
    GUARD
    1.62
    Activations Density 0.080%

    No Known Activations