© 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. 79251
    Prev
    Next
    INDEX
    Explanations

    tf code generation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     AUT
    -0.73
     advierte
    -0.72
    ḗ
    -0.71
    GTA
    -0.69
    繞
    -0.69
     पूर्ण
    -0.67
    Dela
    -0.67
    Timo
    -0.66
     GTA
    -0.66
    ᆨ
    -0.65
    POSITIVE LOGITS
     terra
    1.14
    terraform
    1.13
     providers
    1.13
    Providers
    1.13
     Providers
    1.10
     Terra
    1.08
     provider
    1.08
    providers
    1.02
     Provider
    0.99
     TF
    0.98
    Activations Density 0.046%

    No Known Activations