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. 43
    Prev
    Next
    INDEX
    Explanations

    allergic rhinitis and disorders

    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
    AccessLevel
    -0.86
    慢性
    -0.75
    ן
    -0.74
    ioli
    -0.73
    менно
    -0.72
    ทะ
    -0.70
    scaleY
    -0.70
    ésia
    -0.69
    ≦)
    -0.69
     referrerpolicy
    -0.69
    POSITIVE LOGITS
     Aller
    0.91
    ట్
    0.83
     समीकरण
    0.81
    Aller
    0.81
     Rhin
    0.79
     rhin
    0.79
     encuentre
    0.76
    ופת
    0.75
    )(-
    0.75
     alder
    0.74
    Activations Density 0.073%

    No Known Activations