© 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. 10-GEMMASCOPE-RES-131K
    7. 104357
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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_10/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
    Because
    -2.95
    𞤢
    -2.94
    There
    -2.92
    They
    -2.78
    新的
    -2.77
    That
    -2.75
    When
    -2.70
    We
    -2.61
    .
    -2.58
    While
    -2.53
    POSITIVE LOGITS
    na
    3.05
     he
    2.67
    的吧
    2.53
     You
    2.52
    AdvEx
    2.38
    翃
    2.25
     her
    2.23
     linii
    2.23
     na
    2.20
    
    2.20
    Activations Density 0.011%

    No Known Activations