© 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. 22652
    Prev
    Next
    INDEX
    Explanations

    motivating or inspiring action

    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
    i
    -2.33
     we
    -2.27
    Zubereitung
    -2.16
    इटम
    -1.96
    ]
    -1.92
     ‚
    -1.90
    2
    -1.87
     volto
    -1.85
    ｂ
    -1.84
     バター
    -1.84
    POSITIVE LOGITS
    蚰
    2.22
    .
    2.22
    が欲しい
    2.03
    が取
    2.02
    が付いて
    1.95
    を買う
    1.92
    贲
    1.88
    
    1.84
    踌
    1.84
    磚
    1.84
    Activations Density 0.009%

    No Known Activations