© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100463
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    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
     but
    -1.49
     of
    -1.41
    recently
    -1.34
    빛
    -1.33
    💰
    -1.33
    暂无
    -1.30
    recent
    -1.26
    昀
    -1.23
    
    -1.23
    section
    -1.22
    POSITIVE LOGITS
     that
    1.95
    7
    1.73
     badania
    1.73
    6
    1.64
    િક
    1.54
    4
    1.48
     übri
    1.47
     things
    1.47
     what
    1.46
     muualla
    1.46
    Activations Density 0.080%

    No Known Activations