© 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. 98384
    Prev
    Next
    INDEX
    Explanations

    geographic locations and features

    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
    Τα
    -0.90
    حم
    -0.85
    因為
    -0.83
    خب
    -0.80
    海岸
    -0.80
    SFX
    -0.77
     ஏ
    -0.76
     Tides
    -0.73
     littoral
    -0.72
     virtù
    -0.71
    POSITIVE LOGITS
     offshore
    1.14
     outside
    1.08
     outer
    0.96
    outer
    0.94
     Outside
    0.91
    outside
    0.91
    deep
    0.90
     банка
    0.90
    shelf
    0.89
     OUTSIDE
    0.89
    Activations Density 0.032%

    No Known Activations