© 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. 83136
    Prev
    Next
    INDEX
    Explanations

    places like Ladakh and Nancy

    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
    pur
    -0.83
    わない
    -0.82
    Ac
    -0.75
    vedi
    -0.74
     wept
    -0.70
     Zelda
    -0.70
     Kwa
    -0.70
     váš
    -0.69
    荔
    -0.69
    Zobacz
    -0.69
    POSITIVE LOGITS
     Ladakh
    1.52
     Leh
    1.16
    Lad
    1.08
     apricot
    1.01
    Leh
    0.99
     Buddhist
    0.94
    Nub
    0.92
     leh
    0.91
     apricots
    0.88
     Lad
    0.85
    Activations Density 0.021%

    No Known Activations