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. 7817
    Prev
    Next
    INDEX
    Explanations

    Get transaction

    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
     بهداشتی
    -0.79
    饰演
    -0.77
     pioneer
    -0.77
     medida
    -0.76
     methane
    -0.75
    ochrome
    -0.75
    ูก
    -0.74
     impact
    -0.73
     showered
    -0.73
    ylene
    -0.73
    POSITIVE LOGITS
    broadcast
    0.91
    keepers
    0.91
    mixing
    0.90
    LayoutStyle
    0.88
    Broadcast
    0.85
    voting
    0.84
     mn
    0.83
    Mn
    0.83
    лли
    0.83
    ём
    0.82
    Activations Density 0.006%

    No Known Activations