© 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. 79507
    Prev
    Next
    INDEX
    Explanations

    hoped

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

    The neuron strongly activates on high-frequency function words—especially short prepositions and articles (e.g. “in,” “to,” “of,” “a”).

    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
    معرفی
    -1.15
     pomysł
    -1.08
    استان
    -1.03
    delmi
    -1.02
    autorelease
    -1.00
    hasilkan
    -0.98
    逕
    -0.97
    geoning
    -0.96
    luste
    -0.93
    Переваги
    -0.93
    POSITIVE LOGITS
     "
    1.23
     values
    1.15
     симво
    1.06
     “
    1.01
     human
    1.01
    ;?
    1.00
     reportedly
    0.98
     kämp
    0.98
    <<"
    0.98
    tuce
    0.96
    Activations Density 0.045%

    No Known Activations