© 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. 83108
    Prev
    Next
    INDEX
    Explanations

    guaranteeing or ensuring government loans

    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
    sterdam
    -0.82
     Fiona
    -0.78
    skem
    -0.77
     ecles
    -0.75
    ffions
    -0.73
     Barn
    -0.73
     następu
    -0.72
    ئم
    -0.72
    anyang
    -0.72
    barn
    -0.72
    POSITIVE LOGITS
     guarantee
    3.66
     guarantees
    3.23
     Guarantee
    3.03
     guaranteed
    2.95
    guarantee
    2.80
     guaranteeing
    2.80
    guar
    2.64
    Guarantee
    2.63
     Guarante
    2.55
     Guaranteed
    2.48
    Activations Density 0.025%

    No Known Activations