© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54082
    Prev
    Next
    INDEX
    Explanations

    introductions and questions

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

    The neuron consistently fires on very common function words (articles like “the,” auxiliaries like “are” and “could,” conjunctions like “and,” prepositions like “in”/“on,” etc.).

    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
     recomiendo
    -1.28
     hidupnya
    -1.17
     klinik
    -1.16
     панели
    -1.09
     personaje
    -1.06
     origen
    -1.06
     armario
    -1.06
    kým
    -1.05
     чехол
    -1.04
     "../../../../
    -1.03
    POSITIVE LOGITS
     Especific
    1.21
    يكون
    1.14
     Одна
    1.13
    ましい
    1.13
    ᐢ
    1.12
    örungen
    1.10
    arriver
    1.10
     Añade
    1.06
    ****
    1.06
    vington
    1.06
    Activations Density 0.005%

    No Known Activations