© 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. 79336
    Prev
    Next
    INDEX
    Explanations

    multi- dimensional

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

    The neuron strongly activates on hyphens and the parts of hyphenated compound words.

    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
    的大小
    -1.05
     gênero
    -0.95
    mindedness
    -0.93
     namorado
    -0.93
    itisation
    -0.93
    liken
    -0.93
    ícias
    -0.92
    wist
    -0.91
    bridization
    -0.90
    わから
    -0.90
    POSITIVE LOGITS
    感のある
    1.10
     című
    1.02
     themed
    0.98
     reise
    0.96
     externo
    0.94
     staffed
    0.89
    kenstock
    0.88
     belge
    0.88
     equipped
    0.88
     ziem
    0.86
    Activations Density 0.355%

    No Known Activations