© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107417
    Prev
    Next
    INDEX
    Explanations

    Maasai, Ma'aden, Maala, criteria

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

    The neuron fires strongly on tokens containing the substring “Ma” (e.g. “Maats,” “Ma–3,” “Maangchi,” “Maasai,” “Ma’alouf”).

    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
    garten
    -0.79
    decker
    -0.75
    ую
    -0.75
     Suggested
    -0.75
     Naj
    -0.74
     Britain
    -0.73
    Emerald
    -0.73
     Genoa
    -0.71
    ärke
    -0.69
    QX
    -0.69
    POSITIVE LOGITS
     CRITERIA
    0.87
    Mods
    0.84
     ಮಾ
    0.80
    criterion
    0.78
    的要求
    0.75
     agrees
    0.73
    Criteria
    0.73
     バラ
    0.71
     criteria
    0.70
    thentication
    0.69
    Activations Density 0.029%

    No Known Activations