© 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. 22420
    Prev
    Next
    INDEX
    Explanations

    comes asis setsaid theywas discussingwas seen

    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
     when
    -2.22
     before
    -2.02
     cuando
    -1.96
     while
    -1.88
    Some
    -1.79
    There
    -1.67
    when
    -1.63
     When
    -1.63
    When
    -1.61
     if
    -1.58
    POSITIVE LOGITS
     other
    1.66
    其他
    1.63
     anderen
    1.55
     других
    1.52
     други
    1.52
     другой
    1.52
     다른
    1.50
     gekle
    1.48
    蕺
    1.45
     gekocht
    1.43
    Activations Density 0.109%

    No Known Activations