© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41034
    Prev
    Next
    INDEX
    Explanations

    descriptive clauses using which

    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
    Ꮄ
    -2.23
     navide
    -2.05
    儛
    -1.95
    鼉
    -1.82
     metode
    -1.81
     Sänger
    -1.81
     valla
    -1.80
     города
    -1.79
     faſt
    -1.79
    nąć
    -1.78
    POSITIVE LOGITS
    s
    2.48
     were
    2.38
    ↵
    2.05
    ים
    2.02
    र
    1.98
    n
    1.97
      
    1.88
     is
    1.86
    ing
    1.80
     The
    1.77
    Activations Density 0.008%

    No Known Activations