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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 63
    Prev
    Next
    INDEX
    Explanations

    holy followed by religious or significant nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     craz
    -2.05
     teuer
    -2.03
     craze
    -1.98
    拶
    -1.97
     he
    -1.95
     cameo
    -1.92
    妞
    -1.92
    我去
    -1.90
     premiere
    -1.88
     высоте
    -1.88
    POSITIVE LOGITS
    ]
    2.77
     Saltar
    2.53
     ulter
    2.50
     errore
    2.50
     現貨
    2.48
     奶茶
    2.36
     regata
    2.34
     minori
    2.33
    庒
    2.31
     icona
    2.30
    Activations Density 0.012%

    No Known Activations