© 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. 10-GEMMASCOPE-RES-131K
    7. 67809
    Prev
    Next
    INDEX
    Explanations

    supported employmentelephant sharksequencing of

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

    descriptions of hotel and accommodation locations, particularly distance information from landmarks or amenities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on descriptive attributes and metrics in hotel/property listings—e.g. location, distances, features, and other amenity details.

    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
    sukienka
    -1.44
    Changelog
    -1.40
    üstet
    -1.39
     København
    -1.39
    klar
    -1.36
    
    -1.36
     "*",
    -1.36
    硖
    -1.36
    miot
    -1.34
    ständen
    -1.31
    POSITIVE LOGITS
    It
    1.98
     it
    1.64
     are
    1.58
     It
    1.48
    进入了
    1.36
     erlaubt
    1.33
    それは
    1.32
        
    1.31
    Where
    1.27
     siento
    1.26
    Activations Density 0.006%

    No Known Activations