© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68761
    Prev
    Next
    INDEX
    Explanations

    best corrected, best exercises, best supportive care

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

    the word “best” (especially in phrases like “best-corrected,” “best supportive care,” etc.).

    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
     to
    -2.33
     of
    -2.11
    thenReturn
    -1.66
     ¨
    -1.64
     故
    -1.56
    }
    -1.53
    лены
    -1.52
    готовки
    -1.52
    йка
    -1.50
     ampla
    -1.50
    POSITIVE LOGITS
     xícara
    2.19
     caneca
    1.98
    which
    1.92
     که
    1.91
    what
    1.91
    just
    1.88
    best
    1.86
    that
    1.86
     можете
    1.84
    most
    1.80
    Activations Density 0.021%

    No Known Activations