© 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. 6915
    Prev
    Next
    INDEX
    Explanations

    strength, rigor, or fervor

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

    The neuron flags abstract nouns ending in “-or” or “-our” (e.g. vigor, rigor, fervor, splendor).

    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
    采用了
    -2.83
    哢
    -2.63
    ’)
    -2.63
     setAddress
    -2.58
    )：
    -2.58
    暂无
    -2.58
    .《
    -2.56
    槼
    -2.56
     provides
    -2.52
    玙
    -2.52
    POSITIVE LOGITS
    .
    3.02
    8
    2.94
    2
    2.84
    6
    2.80
    7
    2.77
    9
    2.75
    4
    2.63
    </b>
    2.59
     وأ
    2.56
     MUCH
    2.50
    Activations Density 0.008%

    No Known Activations