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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80674
    Prev
    Next
    INDEX
    Explanations

    doing, ing, providing

    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
    breviations
    -2.39
    Surprisingly
    -1.88
    importation
    -1.81
    𝒔
    -1.80
     '{}
    -1.78
    gencias
    -1.78
    ৄ
    -1.77
    Despite
    -1.76
     الموضوع
    -1.70
    Even
    -1.68
    POSITIVE LOGITS
     the
    2.14
     You
    2.02
    ING
    1.99
     ſont
    1.91
     tornando
    1.90
     deixando
    1.86
    the
    1.83
    璆
    1.81
    蠃
    1.74
     professores
    1.73
    Activations Density 0.032%

    No Known Activations