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. 8658
    Prev
    Next
    INDEX
    Explanations

    Q: or code snippet

    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
     specified
    -0.84
    광
    -0.84
     make
    -0.77
     virtually
    -0.77
     appointed
    -0.75
     fairly
    -0.75
     queue
    -0.74
     kolam
    -0.73
    agory
    -0.72
     Saf
    -0.70
    POSITIVE LOGITS
    titleMargin
    0.82
     concurrency
    0.79
    blage
    0.79
     gespe
    0.78
    Brooks
    0.77
    niť
    0.77
     serenity
    0.77
    oldo
    0.77
     sui
    0.75
    ξε
    0.75
    Activations Density 0.004%

    No Known Activations