© 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. 98868
    Prev
    Next
    INDEX
    Explanations

    blade specifications or servers

    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
    s
    -3.14
    ’
    -3.11
    d
    -2.63
    ❉
    -2.53
     unsere
    -2.47
    昞
    -2.42
    唞
    -2.31
    彣
    -2.27
    ズニー
    -2.22
    韮
    -2.20
    POSITIVE LOGITS
    '
    2.81
    ра
    2.78
     You
    2.77
    可以
    2.73
     если
    2.69
    に
    2.64
     jika
    2.47
     первой
    2.34
     welchem
    2.34
     buscar
    2.34
    Activations Density 0.009%

    No Known Activations