© 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. 34-GEMMASCOPE-RES-131K
    7. 62644
    Prev
    Next
    INDEX
    Explanations

    causes or enables actions

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

    This neuron fires on short uppercase initialisms or acronyms (words composed of consecutive capital letters).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sommes
    -1.34
    のは
    -1.12
     rhestr
    -1.08
    gido
    -1.06
     считают
    -1.05
    }$.
    -0.98
    を開始
    -0.98
     menyerang
    -0.96
     bolsillos
    -0.96
     هستید
    -0.95
    POSITIVE LOGITS
     makes
    3.17
    ทำให้
    3.09
     allows
    2.97
     helps
    2.86
     gives
    2.77
     resulted
    2.72
     باعث
    2.72
     gave
    2.58
     helped
    2.50
     enables
    2.45
    Activations Density 0.359%

    No Known Activations