© 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. 74595
    Prev
    Next
    INDEX
    Explanations

    craftsmanship and workmanship

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

    the presence of words referring to skilled manual craft or quality workmanship.

    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
    ᠂
    -2.20
    鉨
    -2.19
     directivos
    -2.19
     diputados
    -2.05
    锖
    -2.02
     históricas
    -1.99
    chuckles
    -1.98
     urbanas
    -1.97
     avendo
    -1.95
     ganti
    -1.92
    POSITIVE LOGITS
    .
    2.94
     craftsmanship
    2.67
    He
    2.45
    T
    2.39
    E
    2.28
    In
    2.27
    H
    2.25
    1
    2.19
    G
    2.17
    </td>
    2.09
    Activations Density 0.002%

    No Known Activations