© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58219
    Prev
    Next
    INDEX
    Explanations

    fairly well

    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
    Negative Logits
    5
    -2.77
    4
    -2.31
    6
    -2.06
    org
    -1.91
    3
    -1.83
    8
    -1.80
     of
    -1.75
    9
    -1.73
     \
    -1.70
    了一個
    -1.66
    POSITIVE LOGITS
    谘
    1.91
    gigi
    1.66
    yamaha
    1.64
    igrette
    1.63
    cupcake
    1.61
    fortnite
    1.59
    noob
    1.53
     онъ
    1.53
     piaci
    1.52
    kawaii
    1.50
    Activations Density 0.011%

    No Known Activations