© 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. 100158
    Prev
    Next
    INDEX
    Explanations

    em dash

    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
     даже
    -2.14
    啭
    -2.11
    ccccccc
    -1.88
     tutte
    -1.87
     einzige
    -1.86
     toate
    -1.79
     Unterschied
    -1.79
     критери
    -1.78
     istruzioni
    -1.77
    除了
    -1.73
    POSITIVE LOGITS
     they
    2.36
     was
    2.17
    寕
    2.06
     that
    2.03
     until
    1.98
     which
    1.94
     have
    1.83
     but
    1.76
     because
    1.74
     helped
    1.73
    Activations Density 0.017%

    No Known Activations