© 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. 38544
    Prev
    Next
    INDEX
    Explanations

    street, sidewalk, boulevard, cafe

    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
     empate
    -0.77
    assertEqual
    -0.72
     roads
    -0.71
     fade
    -0.70
     Harrington
    -0.69
     lepas
    -0.68
     informatique
    -0.66
     falar
    -0.66
    うる
    -0.66
    iness
    -0.65
    POSITIVE LOGITS
     cafes
    0.95
     caf
    0.94
     cafe
    0.94
     café
    0.92
    Café
    0.84
     cafés
    0.84
     Chalk
    0.82
     chalk
    0.81
     CAFE
    0.79
    ревно
    0.76
    Activations Density 0.025%

    No Known Activations