© 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. 84080
    Prev
    Next
    INDEX
    Explanations

    gaining entry or admission

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

    The neuron fires on very high–frequency function words (common stop words like “to,” “be,” “in,” “the,” “a,” “with,” 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
     <",
    -1.00
    不便
    -0.98
    Vorlage
    -0.95
     birbir
    -0.94
    橚
    -0.94
    żyć
    -0.94
    Cyfarwyddwr
    -0.93
    有些不
    -0.92
    Its
    -0.91
     منذ
    -0.91
    POSITIVE LOGITS
     desired
    1.30
     into
    1.25
     in
    1.15
     because
    1.11
     desirable
    1.09
    desired
    1.09
     those
    1.06
     slots
    1.03
     entry
    1.02
     îna
    0.98
    Activations Density 0.023%

    No Known Activations