© 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. 22-GEMMASCOPE-RES-131K
    7. 35288
    Prev
    Next
    INDEX
    Explanations

    Estimation of, Product details, Q:

    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_22/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
     Batalla
    -0.97
    𝗜
    -0.96
    scrollView
    -0.96
    š
    -0.95
    Makanan
    -0.95
    ŗ
    -0.95
     oeil
    -0.91
    ☦
    -0.90
    flops
    -0.89
     Aé
    -0.88
    POSITIVE LOGITS
     others
    1.30
     other
    1.26
     anderer
    1.13
     다른
    0.94
     another
    0.93
     it
    0.92
     другим
    0.92
    同じく
    0.91
     benach
    0.89
     adjacent
    0.86
    Activations Density 0.005%

    No Known Activations