© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45519
    Prev
    Next
    INDEX
    Explanations

    setting something up

    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
     proveniente
    -1.84
    2
    -1.82
    despite
    -1.80
     Quando
    -1.70
     spectacular
    -1.67
     renowned
    -1.66
    ↵
    -1.66
     нынеш
    -1.65
    both
    -1.63
     mediocre
    -1.59
    POSITIVE LOGITS
     a
    2.17
     Some
    1.99
     establishes
    1.86
     by
    1.82
     for
    1.77
     hombres
    1.75
     believes
    1.74
    !!!!!
    1.70
    ,’”
    1.66
    ?”
    1.65
    Activations Density 0.074%

    No Known Activations