© 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. 45647
    Prev
    Next
    INDEX
    Explanations

    Q: and HAMLET:

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

    The neuron strongly activates on very long whitespace‐only tokens (e.g. large blocks of spaces or newlines).

    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
    0
    -3.97
    2
    -3.22
    ↵
    -3.22
    Before
    -3.11
    3
    -3.03
    It
    -2.98
    -
    -2.94
     Before
    -2.83
    With
    -2.81
    1
    -2.80
    POSITIVE LOGITS
    埽
    2.95
    튿
    2.81
    櫪
    2.77
    の説明
    2.70
    🫅
    2.69
    籀
    2.67
    읭
    2.67
    蟳
    2.66
    饧
    2.66
    癭
    2.63
    Activations Density 0.001%

    No Known Activations