© 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. 65664
    Prev
    Next
    INDEX
    Explanations

    street and road infrastructure

    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
     Saks
    -0.79
    פיל
    -0.76
     portata
    -0.75
    GetInstance
    -0.75
    bilidade
    -0.74
    bondale
    -0.73
    Ikr
    -0.71
     Tenant
    -0.71
     confirmación
    -0.70
    Puma
    -0.69
    POSITIVE LOGITS
     streets
    1.75
     street
    1.69
    street
    1.43
     Street
    1.41
     Streets
    1.38
     STREET
    1.33
    Street
    1.32
    streets
    1.26
    STREET
    1.15
     dedication
    1.03
    Activations Density 0.018%

    No Known Activations