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. 8109
    Prev
    Next
    INDEX
    Explanations

    software code and licenses

    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
     libra
    -0.66
     ам
    -0.61
    iger
    -0.60
     Dox
    -0.59
     masks
    -0.59
     SRI
    -0.59
    JpaRepository
    -0.59
    ansa
    -0.59
     gelir
    -0.59
     Hutchison
    -0.58
    POSITIVE LOGITS
     químicos
    0.72
     Plumbing
    0.69
    spiel
    0.69
    frage
    0.68
    自动化
    0.67
     Spotlight
    0.64
     ruch
    0.63
    Poverty
    0.63
    compute
    0.62
     biznes
    0.62
    Activations Density 0.072%

    No Known Activations