© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109644
    Prev
    Next
    INDEX
    Explanations

    use of or application

    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
     maske
    -0.96
    etheless
    -0.92
    참고
    -0.91
     selera
    -0.90
     hijau
    -0.88
    般的
    -0.88
    ısından
    -0.87
    ミラー
    -0.85
    gründe
    -0.85
     markt
    -0.85
    POSITIVE LOGITS
     of
    1.55
    fulness
    1.34
     Use
    1.15
    fully
    1.13
     fulness
    1.10
     ਲਈ
    1.10
    age
    1.05
    िता
    1.02
     patterns
    0.96
    場面
    0.94
    Activations Density 0.077%

    No Known Activations