© 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. 47998
    Prev
    Next
    INDEX
    Explanations

    scenic views from 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_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
    illes
    -0.84
    auml
    -0.83
     シェ
    -0.83
    demia
    -0.82
    acetyl
    -0.82
    瀑布
    -0.82
    état
    -0.81
     început
    -0.79
     تث
    -0.79
    んでも
    -0.79
    POSITIVE LOGITS
     overlooking
    2.80
     overlook
    2.11
     overlooks
    2.08
     views
    1.91
     looking
    1.88
     offers
    1.88
     offering
    1.84
     affording
    1.76
     commanding
    1.73
     affords
    1.70
    Activations Density 0.025%

    No Known Activations