© 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. 22-GEMMASCOPE-RES-131K
    7. 104321
    Prev
    Next
    INDEX
    Explanations

    #include <android>

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

    This neuron identifies positively toned, affective words conveying affection or optimism (e.g. “precious,” “loved,” “free,” “perfect”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kovo
    -0.85
    смотреть
    -0.83
     unusually
    -0.82
    ୈ
    -0.78
     méthode
    -0.78
     kú
    -0.77
     szer
    -0.76
    Кон
    -0.75
     nails
    -0.74
    StringBuffer
    -0.73
    POSITIVE LOGITS
    ांकि
    0.91
     '{{
    0.91
     mentre
    0.86
     ecuador
    0.85
     pimp
    0.85
    teria
    0.84
     descobrir
    0.84
     entdeckt
    0.84
     puta
    0.81
     taiwan
    0.81
    Activations Density 0.004%

    No Known Activations