© 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. 34-GEMMASCOPE-RES-131K
    7. 106116
    Prev
    Next
    INDEX
    Explanations

    Mathematical operations and queries

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     certain
    -1.45
     Certain
    -1.16
    很多的
    -1.09
    นั้น
    -1.07
    Certain
    -1.06
    mpotent
    -1.06
    以前的
    -1.04
     bestimmte
    -1.00
    很高
    -1.00
     многие
    -0.99
    POSITIVE LOGITS
     the
    2.20
     your
    1.27
     alebo
    1.23
     florales
    1.21
     yourself
    1.20
     nimmer
    1.14
     each
    1.12
     två
    1.10
    ţele
    1.10
     and
    1.08
    Activations Density 0.065%

    No Known Activations