© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118570
    Prev
    Next
    INDEX
    Explanations

    collections of data structures

    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
    ParseException
    -0.82
     белая
    -0.74
     Hartford
    -0.73
    IZACIÓN
    -0.73
    menina
    -0.71
    國際
    -0.71
    layoutControl
    -0.70
    totalPage
    -0.70
    ómo
    -0.70
    Pneum
    -0.69
    POSITIVE LOGITS
    NSMutableArray
    1.07
     collections
    1.02
    Resizable
    0.98
    ArrayList
    0.97
    list
    0.93
     deque
    0.91
     associative
    0.91
     ArrayList
    0.90
    HashMap
    0.90
    RB
    0.90
    Activations Density 0.129%

    No Known Activations