© 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. 114243
    Prev
    Next
    INDEX
    Explanations

    actions and states

    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
     who
    -1.71
    tatuaje
    -1.55
    quién
    -1.55
     productores
    -1.52
    Quién
    -1.50
    っていました
    -1.46
    Արտաքին
    -1.44
     maravilh
    -1.43
     każdego
    -1.41
     dibujado
    -1.40
    POSITIVE LOGITS
     and
    1.76
     himself
    1.63
     связан
    1.44
     two
    1.39
     to
    1.39
    部分
    1.36
     \
    1.30
    🤤
    1.30
    5
    1.27
     trov
    1.26
    Activations Density 0.935%

    No Known Activations