© 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. 70190
    Prev
    Next
    INDEX
    Explanations

    code identifiers and keywords

    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
     Reino
    -0.79
     began
    -0.78
     begins
    -0.76
     Suction
    -0.75
     begin
    -0.74
     undeniably
    -0.73
     gives
    -0.72
     now
    -0.72
    ölkerung
    -0.71
     chakras
    -0.70
    POSITIVE LOGITS
    
    0.93
     FIELD
    0.92
     refugiados
    0.89
    version
    0.86
    flg
    0.86
     desecha
    0.85
    ິ
    0.85
     salvajes
    0.85
    isit
    0.83
    ology
    0.83
    Activations Density 0.003%

    No Known Activations