© 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. 1732
    Prev
    Next
    INDEX
    Explanations

    addressing problems and drawbacks

    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
     acestea
    -1.06
    illant
    -1.02
     esfuerzo
    -0.94
     a
    -0.93
     简介
    -0.92
     다른
    -0.91
    複数の
    -0.90
    ()?;
    -0.90
    iligten
    -0.89
     fisuras
    -0.89
    POSITIVE LOGITS
     some
    4.72
     někter
    3.64
     many
    3.23
     algunas
    3.16
     algunos
    3.16
     некоторые
    3.11
     niektor
    3.06
     alcuni
    2.97
     algumas
    2.97
    一些
    2.95
    Activations Density 0.136%

    No Known Activations