© 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. 6719
    Prev
    Next
    INDEX
    Explanations

    language imports

    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
    Negative Logits
    ’,
    -1.63
    ↵
    -1.58
    ”,
    -1.56
    }
    -1.45
     koska
    -1.37
    In
    -1.35
     voidaan
    -1.34
     a
    -1.31
    },
    -1.30
     Health
    -1.30
    POSITIVE LOGITS
    歺
    1.80
    䛗
    1.68
    犼
    1.66
    
    1.65
    ricanes
    1.64
    圌
    1.64
     herbes
    1.59
     assister
    1.59
    蚡
    1.52
    ⏑
    1.52
    Activations Density 0.024%

    No Known Activations