© 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. 72074
    Prev
    Next
    INDEX
    Explanations

    personal possession

    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
     to
    -1.77
    n
    -1.66
    s
    -1.61
     including
    -1.47
    вання
    -1.46
     "
    -1.38
     наиболее
    -1.30
     each
    -1.27
     özellikle
    -1.27
     этих
    -1.22
    POSITIVE LOGITS
     duas
    1.65
     asesinado
    1.63
    ٤
    1.62
    哧
    1.61
     condenado
    1.57
     governador
    1.56
     engraçado
    1.56
    hasilkan
    1.55
    美国的
    1.54
     herido
    1.52
    Activations Density 0.051%

    No Known Activations