© 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. 34-GEMMASCOPE-RES-131K
    7. 106118
    Prev
    Next
    INDEX
    Explanations

    translation `message` or `API`

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     folic
    -0.81
    ᛏ
    -0.80
    `.`
    -0.80
    dde
    -0.79
    alde
    -0.79
    ་བ
    -0.75
    جلس
    -0.74
    zeera
    -0.73
     ROG
    -0.71
     Crema
    -0.71
    POSITIVE LOGITS
     //$
    1.52
    //$
    1.11
     messages
    0.98
    Messages
    0.98
     Messages
    0.97
     cheap
    0.85
    essages
    0.82
    cheap
    0.80
    傚
    0.79
    Leather
    0.78
    Activations Density 0.024%

    No Known Activations