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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8899
    Prev
    Next
    INDEX
    Explanations

    academic and medical assessment

    np_acts-logits-general · gemini-2.5-flash-lite

    text related to academic institutions and educational resources.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     *>(
    -0.91
     сливо
    -0.90
    imachinery
    -0.87
    董事长
    -0.85
     Packet
    -0.85
    遛
    -0.83
    ologic
    -0.83
     ингреди
    -0.83
     wees
    -0.82
     сыром
    -0.82
    POSITIVE LOGITS
     campus
    1.54
     Faculty
    1.50
    Faculty
    1.43
     student
    1.42
     staff
    1.32
    student
    1.25
    campus
    1.24
     students
    1.23
     faculty
    1.12
    faculty
    1.12
    Activations Density 0.024%

    No Known Activations