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. 7988
    Prev
    Next
    INDEX
    Explanations

    column labels and competitions

    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
     점
    -0.73
     Latham
    -0.72
    ticias
    -0.69
    Transactions
    -0.66
    
    -0.65
    ininger
    -0.64
    TextMessage
    -0.64
    ysuckle
    -0.64
    GENERAL
    -0.63
     Weil
    -0.63
    POSITIVE LOGITS
    Lob
    0.76
     narcotic
    0.70
    坐标
    0.69
    తో
    0.66
    ]=>
    0.66
    ⫾
    0.66
     fruity
    0.65
    xba
    0.65
     tekrar
    0.63
     berdiri
    0.63
    Activations Density 0.077%

    No Known Activations