© 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. 22-GEMMASCOPE-RES-131K
    7. 127783
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on relatively rare, high–information‐content content words (e.g. specialized technical or domain‐specific terms).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    first words in phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     gigantic
    -1.29
     decidedly
    -1.17
     juxtaposition
    -1.15
     grandiose
    -1.15
     monstrous
    -1.15
     startling
    -1.13
    Vezi
    -1.13
    另外
    -1.13
     colossal
    -1.12
     momentous
    -1.12
    POSITIVE LOGITS
     this
    1.87
     what
    1.50
     before
    1.48
     after
    1.41
     when
    1.24
     that
    1.24
     each
    1.21
     while
    1.20
     which
    1.20
     váy
    1.17
    Activations Density 0.075%

    No Known Activations