© 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. 22-GEMMASCOPE-RES-131K
    7. 36556
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
     espel
    -1.30
     juiste
    -1.19
     velha
    -1.17
    鷂
    -1.14
    が一番
    -1.12
     verändert
    -1.10
     Materiales
    -1.10
    
    -1.09
    cterms
    -1.09
     decidido
    -1.09
    POSITIVE LOGITS
    
    1.44
    ❉
    1.32
    1.31
    èges
    1.28
    áló
    1.26
    but
    1.25
     but
    1.22
    wisata
    1.20
    ctile
    1.19
    ropractor
    1.18
    Activations Density 0.005%
    No Known Activations