© 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. 34-GEMMASCOPE-RES-131K
    7. 59589
    Prev
    Next
    INDEX
    Explanations

    so...that consequences

    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_34/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
     so
    -1.49
    那么
    -1.43
     также
    -1.28
     such
    -1.24
     thì
    -1.16
    そんな
    -1.16
    Also
    -1.12
    那麼
    -1.12
     because
    -1.11
    这么
    -1.08
    POSITIVE LOGITS
     almost
    2.20
     hardly
    1.89
     scarcely
    1.78
     practically
    1.76
     barely
    1.75
     even
    1.71
     prácticamente
    1.62
     sogar
    1.56
     nearly
    1.55
     навіть
    1.50
    Activations Density 0.033%

    No Known Activations