© 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. 116012
    Prev
    Next
    INDEX
    Explanations

    analysis and determination

    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
    urally
    -0.84
     handeln
    -0.78
     doporu
    -0.77
     Verkaufs
    -0.77
     interven
    -0.77
     Đi
    -0.76
     mellan
    -0.75
     prouve
    -0.75
     prawa
    -0.75
     obtenido
    -0.73
    POSITIVE LOGITS
     analysis
    2.66
     analyses
    2.34
    分析
    2.09
    analysis
    1.98
     determination
    1.95
     분석
    1.91
    ANALYSIS
    1.90
    Analysis
    1.90
     ANALYSIS
    1.90
     Analysis
    1.75
    Activations Density 0.194%

    No Known Activations