© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111725
    Prev
    Next
    INDEX
    Explanations

    Prague, Flynn, arrayOf, randint

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "Prague" (the city name).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ).
    -2.83
    ’
    -2.64
     You
    -2.59
    を表示
    -2.47
    🧌
    -2.38
     marvels
    -2.33
     möglicherweise
    -2.33
     say
    -2.30
    
    -2.30
                    
    -2.27
    POSITIVE LOGITS
    ﮩ
    2.61
     melap
    2.59
     memutus
    2.58
    
    2.47
     menggelar
    2.44
    琑
    2.42
     mendat
    2.41
     nimmer
    2.38
    ſſel
    2.36
    有助
    2.34
    Activations Density 0.009%

    No Known Activations