© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69437
    Prev
    Next
    INDEX
    Explanations

    quantities with units

    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
     of
    -2.53
     a
    -2.34
     our
    -2.17
     \&
    -1.80
     tikai
    -1.75
     tuli
    -1.63
     these
    -1.59
    周泽
    -1.51
     this
    -1.48
     ovat
    -1.47
    POSITIVE LOGITS
     těch
    1.71
    两个
    1.65
     they
    1.58
     despues
    1.55
    Herkunft
    1.53
     gesamten
    1.51
    имость
    1.51
    ↵↵
    1.50
    Kilde
    1.50
     inneren
    1.49
    Activations Density 0.016%

    No Known Activations