© 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. 81448
    Prev
    Next
    INDEX
    Explanations

    small and medium-sized businesses

    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
    コスパ
    -0.89
     Senior
    -0.87
     sustent
    -0.81
     россия
    -0.81
     abraço
    -0.80
    äsenti
    -0.79
    restle
    -0.79
    ガキ
    -0.78
     ayaa
    -0.77
    ped
    -0.77
    POSITIVE LOGITS
     enterprises
    1.45
     enterprise
    1.23
     business
    1.09
     businesses
    1.07
    企业
    1.06
    enterprise
    1.02
    medium
    1.00
     sized
    0.98
     medium
    0.97
    Medium
    0.94
    Activations Density 0.023%

    No Known Activations