© 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. 13667
    Prev
    Next
    INDEX
    Explanations

    based followed by a location and an entity

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

    This neuron detects mentions of organizations or people described as “based” in a specific location.

    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
     используют
    -1.70
     there
    -1.60
    ﮧ
    -1.58
     melibatkan
    -1.53
     here
    -1.52
    使う
    -1.49
     nouvelles
    -1.47
     has
    -1.46
     riguarda
    -1.44
    astră
    -1.42
    POSITIVE LOGITS
     ‚
    1.63
     två
    1.56
     \_
    1.54
     ваш
    1.52
    </tfoot>
    1.52
    eleste
    1.50
     Kilometer
    1.48
     наших
    1.45
    titudes
    1.45
    geſ
    1.45
    Activations Density 0.020%

    No Known Activations