© 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. 75638
    Prev
    Next
    INDEX
    Explanations

    career/personal bests and records

    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
     career
    -1.31
    career
    -1.12
    Career
    -0.99
     CAREER
    -0.94
     Career
    -0.92
    Careers
    -0.88
     карьер
    -0.84
    گاری
    -0.83
    uração
    -0.82
    medieval
    -0.81
    POSITIVE LOGITS
     best
    2.02
    best
    1.76
     Best
    1.36
    Best
    1.34
     BEST
    1.31
     high
    1.27
    BEST
    1.21
     legjobb
    1.20
     worst
    1.13
     besten
    1.12
    Activations Density 0.015%

    No Known Activations