© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22527
    Prev
    Next
    INDEX
    Explanations

    largely + verb

    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
     than
    -1.73
    するの
    -1.48
    )
    -1.48
    роваться
    -1.38
     is
    -1.38
    rapeau
    -1.35
     condenado
    -1.35
     Yet
    -1.34
    such
    -1.31
    ࿚
    -1.31
    POSITIVE LOGITS
     alfo
    1.54
     dezelfde
    1.50
     komment
    1.41
     이야
    1.38
     esimer
    1.37
    來說
    1.36
    Crítica
    1.34
     記事
    1.34
     тоже
    1.31
     reorgan
    1.31
    Activations Density 0.031%

    No Known Activations