© 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. 79355
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
    |--
    -0.76
     county
    -0.75
    CDN
    -0.74
    гда
    -0.73
     Memorial
    -0.73
     refugee
    -0.72
     gemeente
    -0.70
    beu
    -0.68
    especie
    -0.68
    orth
    -0.68
    POSITIVE LOGITS
     Python
    3.92
     Java
    3.77
     python
    3.59
     java
    3.42
    python
    3.41
    Java
    3.30
    Python
    3.28
    java
    3.13
     PHP
    2.78
     JavaScript
    2.72
    Activations Density 0.903%

    No Known Activations