© 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. 31997
    Prev
    Next
    INDEX
    Explanations

    outside the box

    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
    謎
    -0.78
     léka
    -0.75
     sulfuric
    -0.75
    aten
    -0.74
     sulphuric
    -0.72
    κτηρισ
    -0.72
    ඳ
    -0.71
    ៉
    -0.71
    FileDescriptor
    -0.71
    aroni
    -0.71
    POSITIVE LOGITS
     outside
    3.61
    outside
    2.86
    Outside
    2.63
     out
    2.55
     Outside
    2.48
     fuori
    2.36
     fuera
    2.27
     OUTSIDE
    2.08
     خارج
    2.08
    OUTSIDE
    1.97
    Activations Density 0.012%

    No Known Activations