© 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. 98667
    Prev
    Next
    INDEX
    Explanations

    what happens when

    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
     asesin
    -1.93
     desafios
    -1.90
     lác
    -1.88
     medición
    -1.87
    ፳
    -1.81
     réfrig
    -1.79
    臜
    -1.76
     semelh
    -1.75
    薆
    -1.74
     síntesis
    -1.73
    POSITIVE LOGITS
     in
    2.44
     if
    2.39
     about
    2.16
     when
    2.16
     through
    1.95
     Often
    1.89
     unique
    1.87
     from
    1.85
    ↵↵
    1.85
     this
    1.83
    Activations Density 0.016%

    No Known Activations