© 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. 10-GEMMASCOPE-RES-131K
    7. 42533
    Prev
    Next
    INDEX
    Explanations

    noticed especially or missed

    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_10/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
     Whenever
    -1.19
     аналоги
    -1.17
    carian
    -1.15
     Recently
    -1.12
    缔
    -1.11
     Sometimes
    -1.10
    Similar
    -1.08
    czna
    -1.06
     always
    -1.05
    <strong>
    -1.04
    POSITIVE LOGITS
    
    1.45
    栳
    1.35
    matters
    1.35
     kurulan
    1.33
     werd
    1.23
    odle
    1.22
     каждому
    1.22
    plevel
    1.21
     çekilen
    1.20
     hadde
    1.20
    Activations Density 0.025%

    No Known Activations