© 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. 77622
    Prev
    Next
    INDEX
    Explanations

    both

    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
     Each
    -1.18
     for
    -1.14
     or
    -1.06
     because
    -0.98
    大さじ
    -0.92
     where
    -0.90
     by
    -0.89
    あくまで
    -0.88
    Each
    -0.85
     właśnie
    -0.85
    POSITIVE LOGITS
     both
    8.06
     både
    6.75
    both
    6.28
     zarówno
    5.97
     zowel
    5.75
     sowohl
    5.47
    Both
    5.38
    ทั้ง
    5.00
     BOTH
    4.63
    BOTH
    4.47
    Activations Density 0.363%

    No Known Activations