© 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. 42240
    Prev
    Next
    INDEX
    Explanations

    engrave, engraving, engraver, engravement

    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
    謦
    -2.50
     castig
    -2.44
    ᠂
    -2.27
     protégé
    -2.25
    ⢓
    -2.23
    2
    -2.16
    6
    -2.14
    みたら
    -2.14
    缡
    -2.14
    艄
    -2.13
    POSITIVE LOGITS
     now
    2.56
     głó
    2.44
     of
    2.22
    訛
    2.20
     theres
    2.20
    欵
    2.14
    镚
    2.09
     zwart
    2.03
     ваши
    2.02
     merkezi
    2.02
    Activations Density 0.005%

    No Known Activations