© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27536
    Prev
    Next
    INDEX
    Explanations

    business offerings and services

    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_22/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
    ureusement
    -1.09
     there
    -1.08
     but
    -1.05
    அ
    -0.96
    有问题
    -0.96
     because
    -0.94
     that
    -0.94
    breviations
    -0.94
     time
    -0.93
    mande
    -0.91
    POSITIVE LOGITS
     customers
    1.19
     exé
    1.14
     clients
    1.14
     함께
    1.10
     mutually
    1.09
    荚
    1.03
    Cuen
    1.03
     profondément
    1.02
     quidem
    1.02
    γραφία
    1.01
    Activations Density 0.074%

    No Known Activations