© 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. 22-GEMMASCOPE-RES-131K
    7. 25684
    Prev
    Next
    INDEX
    Explanations

    Konner, many, large

    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
    
    -1.51
    垄
    -1.29
     другую
    -1.27
    镲
    -1.27
     คา
    -1.26
    她们
    -1.24
     exemplaire
    -1.24
     oiseau
    -1.23
    =\"
    -1.22
    蛏
    -1.21
    POSITIVE LOGITS
     many
    1.64
     large
    1.59
     enormous
    1.56
     what
    1.52
     so
    1.51
     big
    1.50
     even
    1.47
     it
    1.34
     Even
    1.34
     massive
    1.34
    Activations Density 0.038%

    No Known Activations