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. 8041
    Prev
    Next
    INDEX
    Explanations

    recent national and international guidelines

    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
     цене
    -0.74
    日记
    -0.74
     ra
    -0.71
    tisol
    -0.69
    IFS
    -0.69
    lllllllll
    -0.69
    sendKeys
    -0.68
    ordination
    -0.67
    ység
    -0.67
     at
    -0.67
    POSITIVE LOGITS
     guidelines
    3.53
     guideline
    2.81
     Guidelines
    2.75
     recommendations
    2.66
    guidelines
    2.59
    Guidelines
    2.56
     Guideline
    2.25
     GUIDELINES
    2.22
     recommendation
    2.20
     recommended
    2.02
    Activations Density 0.277%

    No Known Activations