Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8370
    Prev
    Next
    INDEX
    Explanations

    Monty Python

    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
     CDU
    -0.73
     Erne
    -0.70
     Manifest
    -0.69
    JECTION
    -0.68
     Cuff
    -0.67
    bubble
    -0.67
     OGSÅ
    -0.66
    rió
    -0.66
    trip
    -0.66
     zapew
    -0.65
    POSITIVE LOGITS
     Monty
    2.97
    Monty
    2.52
     Python
    1.82
    Python
    1.66
     python
    1.52
    spam
    1.48
     PYTHON
    1.42
    python
    1.39
    Spam
    1.38
    PYTHON
    1.38
    Activations Density 0.045%

    No Known Activations