© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47603
    Prev
    Next
    INDEX
    Explanations

    city names and landmarks

    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
     espes
    -0.95
     Beſ
    -0.93
     إذا
    -0.93
    倢
    -0.91
    
    -0.88
    ଙ
    -0.88
     Filosof
    -0.88
     adapté
    -0.88
     prestigio
    -0.87
    wiście
    -0.87
    POSITIVE LOGITS
     Convention
    1.00
    US
    0.91
     Public
    0.90
    その
    0.87
     Art
    0.85
     Ine
    0.84
    ท่าน
    0.82
    wales
    0.81
     Museum
    0.81
     Gene
    0.79
    Activations Density 0.090%

    No Known Activations