© 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. 33268
    Prev
    Next
    INDEX
    Explanations

    Grant followed by name or entity

    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
    ğı
    -1.03
    考え方
    -1.02
    Etimo
    -0.97
    嚆
    -0.94
    闺蜜
    -0.93
    getOrder
    -0.92
    萄
    -0.91
    ného
    -0.91
     musste
    -0.90
    热点
    -0.89
    POSITIVE LOGITS
    making
    1.08
     yaklaşık
    1.06
    चाल
    1.03
     Thornton
    1.02
    stand
    1.01
    yahoo
    1.00
    stalt
    0.98
    This
    0.98
    том
    0.98
    Initially
    0.97
    Activations Density 0.012%

    No Known Activations