© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107435
    Prev
    Next
    INDEX
    Explanations

    purpose or reference

    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
    缨
    -0.93
    ナー
    -0.91
    wiches
    -0.86
    ractable
    -0.85
     ENOUGH
    -0.84
     ć
    -0.84
     Recommend
    -0.82
    要求
    -0.82
    דם
    -0.80
     الإنترنت
    -0.80
    POSITIVE LOGITS
     reference
    3.86
    reference
    2.98
    Reference
    2.55
    REFERENCE
    2.55
     référence
    2.41
     Reference
    2.36
     REFERENCE
    2.34
     referencia
    2.27
    参考
    2.19
     comparison
    1.98
    Activations Density 0.059%

    No Known Activations