© 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. 10-GEMMASCOPE-RES-131K
    7. 74584
    Prev
    Next
    INDEX
    Explanations

    emphasizing honesty or admitting something

    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_10/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
     and
    -1.90
     but
    -1.88
     a
    -1.77
     especially
    -1.74
     you
    -1.67
     E
    -1.63
     Some
    -1.61
     besonders
    -1.57
     P
    -1.52
     Here
    -1.52
    POSITIVE LOGITS
     gewi
    1.86
     uly
    1.84
     nimmer
    1.74
     uan
    1.73
     omt
    1.70
     teater
    1.66
     friv
    1.65
     zoude
    1.65
     vermi
    1.64
     seks
    1.63
    Activations Density 0.014%

    No Known Activations