© 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. 127686
    Prev
    Next
    INDEX
    Explanations

    distance from a place

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

    The neuron detects numeric distance values (e.g. measurements in kilometers or miles).

    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
    叒
    -1.59
    ܇
    -1.51
     namorados
    -1.48
    SPECIFICATIONS
    -1.48
    unikasi
    -1.45
    峩
    -1.43
    🧎
    -1.40
    Legenda
    -1.39
     deemed
    -1.37
     curta
    -1.35
    POSITIVE LOGITS
     of
    2.86
     from
    2.05
        
    1.64
      
    1.51
    //
    1.46
    -
    1.35
     to
    1.34
    瘫
    1.34
    from
    1.30
       
    1.29
    Activations Density 0.027%

    No Known Activations