© 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. 33774
    Prev
    Next
    INDEX
    Explanations

    numbers, equations, and measurements

    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
     biela
    -1.95
     spise
    -1.88
     ledig
    -1.78
     vernis
    -1.76
     manualidades
    -1.75
     peluche
    -1.74
     kado
    -1.73
     virke
    -1.73
     cerdas
    -1.73
     laine
    -1.72
    POSITIVE LOGITS
    al
    1.70
    8
    1.61
     freakin
    1.61
    ar
    1.54
    and
    1.54
    er
    1.52
     a
    1.51
    了许多
    1.45
    5
    1.45
    :
    1.44
    Activations Density 0.007%

    No Known Activations