© 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. 83998
    Prev
    Next
    INDEX
    Explanations

    strong feelings or dispositions

    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
     the
    -1.46
     sencillos
    -1.42
     motivadoras
    -1.34
     distinto
    -1.34
     that
    -1.30
    я
    -1.27
    感覺
    -1.23
    不一樣
    -1.23
    一个小
    -1.20
    ञ
    -1.20
    POSITIVE LOGITS
    ouncements
    1.33
    äld
    1.33
     However
    1.31
    谙
    1.27
    κίνη
    1.27
    ⟝
    1.27
    𝚣
    1.25
    蒾
    1.24
    nischer
    1.23
     bancada
    1.23
    Activations Density 0.058%

    No Known Activations