© 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. 114176
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     zarówno
    -1.98
    Ջ
    -1.50
    NOWLEDG
    -1.40
    När
    -1.38
    ☹
    -1.32
     PUSTAKA
    -1.31
    ೫
    -1.31
     dieser
    -1.31
     đị
    -1.30
    ANZE
    -1.30
    POSITIVE LOGITS
     they
    2.20
     the
    1.88
     last
    1.61
     their
    1.45
     at
    1.43
     —
    1.34
     just
    1.27
     only
    1.23
     on
    1.22
     didn
    1.22
    Activations Density 0.111%

    No Known Activations