© 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. 98815
    Prev
    Next
    INDEX
    Explanations

    According to Kinin

    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
     your
    -2.13
     our
    -1.64
     the
    -1.60
     grego
    -1.59
     its
    -1.55
     sacó
    -1.55
    Because
    -1.53
    orgeous
    -1.51
    了你
    -1.50
     this
    -1.47
    POSITIVE LOGITS
     was
    1.63
    bereiche
    1.57
     skrev
    1.57
    💁
    1.56
     pasaran
    1.55
     situasi
    1.55
    😞
    1.53
     bricola
    1.52
    gebiete
    1.49
     mentale
    1.46
    Activations Density 0.010%

    No Known Activations