© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38255
    Prev
    Next
    INDEX
    Explanations

    person name or title

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

    The neuron strongly activates on double‐quote characters that introduce or enclose legal case names or titles.

    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
    iações
    -1.17
    viembre
    -1.05
    Erstellt
    -1.04
     prüfen
    -1.04
    Роз
    -1.03
    那些
    -1.02
     fazem
    -1.00
    lji
    -0.99
    Não
    -0.99
    Alguns
    -0.99
    POSITIVE LOGITS
     of
    1.24
    があり
    1.24
    方針
    1.16
     to
    1.13
    が
    1.12
    時間は
    1.08
     sözler
    1.00
     poète
    0.99
    dagogik
    0.98
    時間も
    0.98
    Activations Density 0.001%

    No Known Activations