© 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. 47083
    Prev
    Next
    INDEX
    Explanations

    influenced by

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

    The neuron is simply firing on very high‐frequency (common) tokens—it highlights tokens that occur often in the corpus.

    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
    Focus
    -0.86
     Focus
    -0.83
    の様子
    -0.82
    heiser
    -0.81
    transformer
    -0.79
     प्रदान
    -0.78
    ؐ
    -0.76
     förra
    -0.75
    Ratio
    -0.74
     związ
    -0.74
    POSITIVE LOGITS
     influences
    3.09
     Influences
    2.48
     influence
    2.36
     influenced
    2.25
    Influ
    2.19
    influ
    2.06
    influence
    2.02
    Influence
    2.00
     inspirations
    1.95
    influenced
    1.92
    Activations Density 0.050%

    No Known Activations