© 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. 68403
    Prev
    Next
    INDEX
    Explanations

    I'm asking about code or concepts

    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
    詣
    -1.90
    大部分
    -1.88
    ,
    -1.81
     nachher
    -1.79
    Meik
    -1.74
    mitsub
    -1.74
    berserk
    -1.70
    小龙
    -1.63
    odziel
    -1.62
     which
    -1.60
    POSITIVE LOGITS
    the
    2.09
    埽
    2.03
    釤
    2.02
    鲼
    1.91
    tifiable
    1.90
    quilibrium
    1.88
    volent
    1.88
    檍
    1.84
    馓
    1.82
    𖥧
    1.81
    Activations Density 0.153%

    No Known Activations