© 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. 38554
    Prev
    Next
    INDEX
    Explanations

    code headers and declarations

    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
     their
    -2.84
     its
    -1.58
     mereka
    -1.54
     most
    -1.48
     they
    -1.48
     your
    -1.36
     for
    -1.36
     all
    -1.35
     both
    -1.31
    fır
    -1.27
    POSITIVE LOGITS
     figliu
    1.38
     foglie
    1.32
     również
    1.30
    腟
    1.28
     также
    1.28
     réessayer
    1.23
     quieran
    1.23
    ïse
    1.23
     deoarece
    1.23
     acepción
    1.23
    Activations Density 0.000%

    No Known Activations