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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7815
    Prev
    Next
    INDEX
    Explanations

    database query preparation

    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
     Правда
    -0.87
     oysters
    -0.84
    AZIONI
    -0.80
    drück
    -0.77
    ろん
    -0.77
    hassee
    -0.77
     Gainesville
    -0.77
    iempo
    -0.75
    Köln
    -0.75
    kegaard
    -0.73
    POSITIVE LOGITS
     PDO
    1.29
    stmt
    0.99
    sth
    0.96
    PDO
    0.96
    PDOException
    0.95
     rowCount
    0.94
     junction
    0.83
     preparation
    0.83
    зами
    0.83
     Exeter
    0.82
    Activations Density 0.015%

    No Known Activations