© 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. 22750
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with x

    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
    </b>
    -1.88
     of
    -1.49
    a
    -1.44
     being
    -1.41
     ένα
    -1.40
    ха
    -1.31
     ikke
    -1.31
     是
    -1.30
     NDEBUG
    -1.29
    са
    -1.27
    POSITIVE LOGITS
     повече
    1.45
     pasaba
    1.40
    ARANCE
    1.38
     trataba
    1.37
    ută
    1.35
     рассказала
    1.35
     éstas
    1.34
     venía
    1.32
    一辈子
    1.32
    Lithuan
    1.30
    Activations Density 0.091%

    No Known Activations