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. 8545
    Prev
    Next
    INDEX
    Explanations

    Dee Vee Gee Tee Mee start

    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
    SOME
    -1.02
     unending
    -0.95
     gigantic
    -0.89
    thene
    -0.88
     jogador
    -0.86
    SERVICES
    -0.85
     ANOTHER
    -0.83
     jednej
    -0.82
     patience
    -0.82
     AMAZING
    -0.82
    POSITIVE LOGITS
    Several
    1.08
     several
    1.03
    Three
    0.97
     Several
    0.94
    Even
    0.93
    eee
    0.93
    pee
    0.93
    With
    0.91
    Considering
    0.90
    During
    0.88
    Activations Density 0.020%

    No Known Activations