© 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. 29953
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
    ✨:
    -0.93
    CodedInputStream
    -0.90
    systems
    -0.84
     katika
    -0.84
    กับ
    -0.84
    siasi
    -0.81
    циаль
    -0.81
     és
    -0.81
    bujete
    -0.80
    важа
    -0.80
    POSITIVE LOGITS
     these
    1.19
     next
    1.09
    These
    0.99
     These
    0.89
     solito
    0.81
    Usually
    0.79
     left
    0.79
     Vielleicht
    0.79
     other
    0.78
    左右
    0.78
    Activations Density 0.009%

    No Known Activations