© 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. 98640
    Prev
    Next
    INDEX
    Explanations

    professions ending in -logist

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

    The neuron activates on professional titles ending in “-logist” (e.g. nephrologist, meteorologist, psychologist, neurologist, 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
    gebras
    -2.73
     trésor
    -2.53
    čný
    -2.47
    AddTagHelper
    -2.45
    acterísticas
    -2.45
    или
    -2.44
     reduziert
    -2.41
     şir
    -2.39
    摄影
    -2.38
    }$
    -2.36
    POSITIVE LOGITS
    .
    3.89
    ↵
    3.09
    C
    2.86
    U
    2.70
    \
    2.61
    From
    2.50
    end
    2.38
    幸好
    2.36
    MAXN
    2.36
        
    2.36
    Activations Density 0.013%

    No Known Activations