© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    location names and directions

    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
    InputChange
    -0.87
     spô
    -0.83
    Класс
    -0.82
    vić
    -0.81
    上涨
    -0.80
    侪
    -0.78
    𝚌
    -0.78
    デーション
    -0.77
    ombic
    -0.77
    chnung
    -0.77
    POSITIVE LOGITS
     exit
    1.50
     map
    1.45
     entrance
    1.43
     zone
    1.38
     maps
    1.33
     exits
    1.25
     Exit
    1.17
     room
    1.15
     rooms
    1.14
     Entrance
    1.13
    Activations Density 0.021%

    No Known Activations