© 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. 31037
    Prev
    Next
    INDEX
    Explanations

    linking street names

    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
     suburban
    -0.83
     Westchester
    -0.80
    ilyen
    -0.75
    stums
    -0.70
    多摩
    -0.69
    
    -0.68
    geqslant
    -0.68
    tocks
    -0.66
    ≫
    -0.66
     silhouette
    -0.66
    POSITIVE LOGITS
    র
    0.80
    ilitatea
    0.79
     Goethe
    0.71
    soup
    0.71
     Burnley
    0.71
    Fingers
    0.69
     Kuta
    0.69
    صبحت
    0.69
     LocalDateTime
    0.69
     Poisson
    0.68
    Activations Density 0.091%

    No Known Activations