© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67940
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
     of
    -1.71
     információ
    -1.19
    いれば
    -1.06
    ону
    -1.06
    otong
    -1.06
     حتی
    -1.05
     aynı
    -1.05
    செ
    -1.05
    mainwindow
    -1.03
    مشاه
    -1.01
    POSITIVE LOGITS
     those
    1.40
     different
    1.34
      「
    1.21
    غيير
    1.13
     roligt
    1.12
    赜
    1.08
    -),
    1.05
     milieux
    1.05
     });
    
    1.05
     when
    1.05
    Activations Density 0.109%

    No Known Activations