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. 8605
    Prev
    Next
    INDEX
    Explanations

    DX operation

    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
    CS
    -0.72
     inserir
    -0.70
     crickets
    -0.68
    toid
    -0.67
    Gs
    -0.67
     CS
    -0.67
     cs
    -0.67
     тип
    -0.67
     sientes
    -0.66
    instellungen
    -0.66
    POSITIVE LOGITS
     DX
    1.01
     Dx
    0.93
    гою
    0.85
     Worked
    0.85
     operating
    0.83
    DX
    0.82
     operate
    0.81
     portable
    0.79
     operated
    0.79
     Permanente
    0.79
    Activations Density 0.025%

    No Known Activations