© 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. 34-GEMMASCOPE-RES-131K
    7. 83698
    Prev
    Next
    INDEX
    Explanations

    Q: ... , Super secure, The broad, TOP NEWS

    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
     expect
    -0.81
    فيذ
    -0.79
    IJ
    -0.77
     personali
    -0.75
     Это
    -0.74
    Being
    -0.74
    нинград
    -0.72
     expecting
    -0.72
     tiros
    -0.71
     as
    -0.71
    POSITIVE LOGITS
     ladite
    0.87
     embora
    0.86
    谌
    0.85
     distintos
    0.83
     diseñ
    0.82
     posiblemente
    0.82
    MathML
    0.81
    exemple
    0.81
     cuja
    0.80
     queste
    0.79
    Activations Density 0.004%

    No Known Activations