© 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. 47266
    Prev
    Next
    INDEX
    Explanations

    finished with a concluding detail

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

    The neuron is highly tuned to the past‐tense verb “finished” (as used in sports/stat line summaries).

    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
     durante
    -0.98
     obrazy
    -0.95
    Prijs
    -0.94
     SAME
    -0.93
    onyme
    -0.93
    TestBed
    -0.93
     siihen
    -0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.90
    وانید
    -0.90
    ילות
    -0.89
    POSITIVE LOGITS
     with
    2.06
     the
    1.43
     on
    1.27
     at
    1.20
     as
    1.19
     without
    1.15
     behind
    0.96
     ahead
    0.96
     just
    0.92
     atop
    0.90
    Activations Density 0.014%

    No Known Activations