© 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. 59262
    Prev
    Next
    INDEX
    Explanations

    across street or road

    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
     between
    -1.13
     між
    -0.87
     Between
    -0.85
     Fassung
    -0.83
     areas
    -0.83
     zwischen
    -0.82
     Entwurf
    -0.81
     parts
    -0.81
    rovna
    -0.81
    ハツ
    -0.80
    POSITIVE LOGITS
     street
    2.06
     road
    1.70
    street
    1.65
    STREET
    1.34
    Street
    1.32
     дорогу
    1.27
    road
    1.23
     STREET
    1.16
    Road
    1.14
     straat
    1.13
    Activations Density 0.007%

    No Known Activations