© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68510
    Prev
    Next
    INDEX
    Explanations

    names and TV shows

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

    The neuron strongly activates on capitalized tokens—i.e. proper names (people, places, botanical/genus names, film titles, etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vorliegenden
    -1.64
    L
    -1.62
    ☶
    -1.60
    ikusbot
    -1.59
     芽
    -1.59
     ausdrück
    -1.58
    兢
    -1.55
     裕
    -1.55
    ooplankton
    -1.54
     ویکی
    -1.52
    POSITIVE LOGITS
     unser
    1.69
    Tensi
    1.59
    ﺐ
    1.53
    idk
    1.48
    ться
    1.48
    lmao
    1.44
     attendant
    1.44
    是如何
    1.40
    りが
    1.38
     instances
    1.37
    Activations Density 0.006%

    No Known Activations