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. 7985
    Prev
    Next
    INDEX
    Explanations

    PhD, doctorate, postgraduate study, supervision

    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
    yahoo
    -0.73
     Core
    -0.68
     роста
    -0.68
    ンス
    -0.67
    我们将
    -0.65
     instructors
    -0.64
    大学の
    -0.64
     Yahoo
    -0.64
     college
    -0.64
     professor
    -0.64
    POSITIVE LOGITS
     supervisors
    1.85
     Supervisors
    1.74
     supervised
    1.73
     supervisor
    1.66
    supervisor
    1.66
    Supervis
    1.63
    supervised
    1.61
     supervision
    1.59
     Supervision
    1.59
    Supervisor
    1.55
    Activations Density 0.021%

    No Known Activations