© 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. 6849
    Prev
    Next
    INDEX
    Explanations

    for Change, ImageData, SR, Self

    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
     preparando
    -1.99
     navegando
    -1.96
     sabores
    -1.84
     prodej
    -1.80
     departamentos
    -1.77
     tratando
    -1.72
     comiendo
    -1.72
     comprando
    -1.71
     els
    -1.71
     linke
    -1.66
    POSITIVE LOGITS
    4
    2.75
    0
    2.63
    7
    2.53
    5
    2.48
    2
    2.47
    6
    2.20
     Additionally
    2.17
     Another
    2.16
    for
    2.13
    3
    2.11
    Activations Density 0.012%

    No Known Activations