© 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. 34-GEMMASCOPE-RES-131K
    7. 93587
    Prev
    Next
    INDEX
    Explanations

    adjacent or bordering

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

    The neuron activates most strongly on geographic place names (countries, regions, municipalities, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    oba
    -0.84
    immt
    -0.80
    чника
    -0.80
    ρών
    -0.79
    ukkan
    -0.79
    RegressionTest
    -0.78
    weisungen
    -0.78
     แท
    -0.77
     concep
    -0.76
    Inactive
    -0.75
    POSITIVE LOGITS
     bordering
    3.88
     adjacent
    3.58
     border
    3.39
     borders
    3.17
     adjoining
    2.95
    border
    2.94
     bordered
    2.86
     abut
    2.80
    adjacent
    2.69
     Adjacent
    2.59
    Activations Density 0.136%

    No Known Activations