© 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. 103487
    Prev
    Next
    INDEX
    Explanations

    street names or types

    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
     velho
    -0.94
     塔
    -0.94
     countrymen
    -0.90
     forests
    -0.89
    MAXIMUM
    -0.88
    ğimiz
    -0.87
     Inſ
    -0.86
     duele
    -0.85
     mensaje
    -0.85
    menge
    -0.84
    POSITIVE LOGITS
     street
    3.00
     streets
    2.44
     Street
    2.17
    street
    2.14
    Street
    1.84
     STREET
    1.58
    streets
    1.56
    STREET
    1.53
     Streets
    1.48
     улице
    1.37
    Activations Density 0.041%

    No Known Activations