© 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. 68659
    Prev
    Next
    INDEX
    Explanations

    proper names and places

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

    The neuron strongly activates on short character‐sequence fragments of capitalized words—i.e. the letter‐group prefixes or acronyms you see in proper names and technical abbreviations.

    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
     where
    -1.25
     this
    -1.21
    オーストラリア
    -1.16
     before
    -1.11
     at
    -1.10
    Before
    -1.09
    Besos
    -1.05
     showy
    -1.02
     skier
    -1.02
    Without
    -1.02
    POSITIVE LOGITS
     tutaj
    1.30
     vorn
    1.22
     acclaimed
    1.22
     significativo
    1.20
     usado
    1.18
     renowned
    1.18
    ₐ
    1.17
    "><?=
    1.16
    ୌ
    1.15
    ulence
    1.13
    Activations Density 1.077%

    No Known Activations