© 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. 20056
    Prev
    Next
    INDEX
    Explanations

    Algeria and Algiers

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

    The neuron strongly activates on any form of “Algeria” (and its adjective or name variants, including country code DZ and French “Algérie”).

    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
     we
    -2.86
    jaqueta
    -2.81
    pulseira
    -2.53
     alarming
    -2.45
    pecabe
    -2.42
    或者是
    -2.36
    眥
    -2.34
    sudadera
    -2.31
    所需的
    -2.31
    未完
    -2.30
    POSITIVE LOGITS
    1
    3.47
    ‘
    2.47
     \
    2.17
    琑
    2.14
    2
    2.14
    蠓
    2.13
    StreetMap
    2.11
    筇
    2.11
    $,
    2.11
    ación
    2.11
    Activations Density 0.004%

    No Known Activations