© 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. 72198
    Prev
    Next
    INDEX
    Explanations

    not perfect

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

    The neuron fires on occurrences of the word “perfect” (and its variant “imperfect”).

    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
     enjeux
    -1.44
    ンダイ
    -1.36
     województwie
    -1.34
     langer
    -1.30
    patine
    -1.28
    のですか
    -1.27
     wydaje
    -1.24
    
    -1.23
     ‘
    -1.23
     韩
    -1.23
    POSITIVE LOGITS
     but
    1.95
     caract
    1.46
     גם
    1.45
     beschäf
    1.39
    ↵
    1.37
    biendo
    1.34
    いかがでしたか
    1.32
    you
    1.31
     on
    1.30
    ]
    1.30
    Activations Density 0.018%

    No Known Activations