© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117467
    Prev
    Next
    INDEX
    Explanations

    programming import statements

    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
     entrambi
    -0.85
    過ぎ
    -0.84
    /,
    -0.79
     என
    -0.78
     contextLoads
    -0.77
    }(),
    -0.77
    шаго
    -0.76
    #,
    -0.75
     fortsätter
    -0.74
     拼
    -0.73
    POSITIVE LOGITS
    import
    1.75
    ;
    1.22
     import
    1.18
     importing
    1.17
     Importing
    0.90
     Imports
    0.90
    今年は
    0.88
    metros
    0.87
     imports
    0.87
    タグ
    0.87
    Activations Density 0.013%

    No Known Activations