© 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. 33260
    Prev
    Next
    INDEX
    Explanations

    place name identifiers

    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
    cdf
    -0.84
     Gog
    -0.74
    Hale
    -0.71
     Chilean
    -0.69
     MTA
    -0.68
    傣
    -0.68
     trái
    -0.67
    aura
    -0.67
     Westchester
    -0.67
    )->
    -0.66
    POSITIVE LOGITS
     Edmonton
    0.85
    Edmonton
    0.85
     Mop
    0.83
    徳島
    0.81
    レコード
    0.79
     Limoges
    0.75
     математи
    0.75
    sprechend
    0.75
    revista
    0.75
    чение
    0.74
    Activations Density 0.027%

    No Known Activations