© 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. 27166
    Prev
    Next
    INDEX
    Explanations

    every or each

    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
     some
    -1.09
     those
    -1.02
     would
    -1.02
     first
    -0.98
     can
    -0.98
     through
    -0.96
     what
    -0.95
     after
    -0.94
     while
    -0.93
     might
    -0.91
    POSITIVE LOGITS
     every
    1.79
     chaque
    1.73
     каждый
    1.66
     каждую
    1.63
     each
    1.63
     varje
    1.63
     κάθε
    1.62
    Chaque
    1.62
     каждом
    1.61
     setiap
    1.58
    Activations Density 0.097%

    No Known Activations