© 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. 34-GEMMASCOPE-RES-131K
    7. 56809
    Prev
    Next
    INDEX
    Explanations

    iHeartMedia, iDream Jewelry, IFLY

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    '|
    -0.90
    andafter
    -0.83
     ชุด
    -0.81
    SHAPE
    -0.80
    Jg
    -0.80
    couraging
    -0.79
     Theres
    -0.79
     otrzyma
    -0.78
    teng
    -0.78
    mientos
    -0.78
    POSITIVE LOGITS
     myself
    0.85
     yü
    0.79
    piece
    0.78
    ρισσ
    0.78
    What
    0.77
     nuit
    0.76
     donc
    0.75
    Facade
    0.75
    ダース
    0.73
    subprocess
    0.73
    Activations Density 0.042%

    No Known Activations