© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13541
    Prev
    Next
    INDEX
    Explanations

    technical snippets and foreign words

    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_22/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
    
    -1.19
     bello
    -1.12
     lemah
    -1.11
     娘
    -1.09
    徒歩
    -1.06
     pikir
    -1.05
     berikan
    -1.03
     getAccount
    -1.02
     lihat
    -1.02
     mence
    -1.02
    POSITIVE LOGITS
     satisfecho
    1.30
     Urteil
    1.24
     идеально
    1.19
    antlr
    1.11
     viendo
    1.11
     čty
    1.09
     ursprüng
    1.07
     disfrutando
    1.05
    Debate
    1.05
    amazon
    1.04
    Activations Density 0.000%

    No Known Activations