© 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. 20083
    Prev
    Next
    INDEX
    Explanations

    locations and types of accommodations

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

    This neuron specializes in detecting place names and geographic locations (e.g., city or landmark names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    と話
    -1.77
     çünkü
    -1.77
    änderung
    -1.62
     türkiye
    -1.59
     gastronomía
    -1.58
     ecosistema
    -1.53
     différentes
    -1.52
    lanır
    -1.50
     desmotiv
    -1.49
    numericUpDown
    -1.49
    POSITIVE LOGITS
     with
    1.68
     in
    1.62
     InputMaybe
    1.59
     upacara
    1.58
     DOLLARS
    1.57
                    
    1.52
    In
    1.52
     по
    1.48
     –
    1.47
    lesssim
    1.47
    Activations Density 0.072%

    No Known Activations