© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40696
    Prev
    Next
    INDEX
    Explanations

    positive attributes and qualities

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

    This neuron detects positive evaluative adjectives or descriptors that praise or highlight desirable qualities of something.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     they
    -2.38
     you
    -2.22
    ?
    -1.88
    鼋
    -1.67
    FundMe
    -1.67
     it
    -1.67
    滹
    -1.66
    赑
    -1.63
      
    -1.63
     malgré
    -1.62
    POSITIVE LOGITS
     and
    1.80
    懨
    1.73
    梦见
    1.70
     که
    1.67
    }$
    1.63
    中心的
    1.62
     mengerti
    1.60
    lahir
    1.59
    etches
    1.56
    点此
    1.55
    Activations Density 0.067%

    No Known Activations