© 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. 15506
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     aislada
    -2.42
    replyreport
    -2.33
     広場
    -2.23
     protegida
    -2.17
     now
    -2.13
     distritos
    -2.06
     this
    -2.06
    ズニー
    -1.98
     only
    -1.91
    comedy
    -1.88
    POSITIVE LOGITS
     "
    2.19
    </h3>
    2.03
    ↵↵
    2.03
    f
    2.02
    ara
    2.00
    かけ
    2.00
    ar
    1.96
     We
    1.90
     tetapi
    1.89
    ay
    1.88
    Activations Density 0.013%

    No Known Activations