© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16349
    Prev
    Next
    INDEX
    Explanations

    resource script

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

    The neuron specifically activates on the word “resource.”

    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
     fantástica
    -1.03
     maravillosa
    -1.03
     Hül
    -1.02
     zimowa
    -1.02
    晅
    -1.02
    ﱠ
    -1.00
    合理的
    -0.98
    //!
    -0.98
     měsí
    -0.97
     zimowe
    -0.97
    POSITIVE LOGITS
    though
    1.12
    teur
    1.09
     اختی
    1.05
    尤其
    1.01
     by
    0.99
    lesssim
    0.99
    bedür
    0.95
    ידה
    0.95
    を
    0.94
     though
    0.93
    Activations Density 0.000%

    No Known Activations