© 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. 33180
    Prev
    Next
    INDEX
    Explanations

    Kapampangan, public class, question start, Gilmore, reason

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

    The neuron is keyed to the character sequence “amp” wherever it appears in a token.

    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
    ',$
    -0.86
    `,`
    -0.83
    릎
    -0.78
    
    -0.77
    ał
    -0.76
    IRES
    -0.75
     水晶
    -0.75
    lees
    -0.74
    utors
    -0.74
    WebServlet
    -0.73
    POSITIVE LOGITS
    امن
    0.98
    ХОД
    0.78
    ologio
    0.76
    Противо
    0.76
    ไ
    0.75
     blossomed
    0.73
    чены
    0.73
     Apfel
    0.72
    Sådan
    0.71
    贰
    0.71
    Activations Density 0.002%

    No Known Activations