© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118209
    Prev
    Next
    INDEX
    Explanations

    name entities and beginnings

    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
     then
    -0.91
     as
    -0.90
     only
    -0.83
    essura
    -0.82
     usually
    -0.80
     several
    -0.79
     tuvieron
    -0.77
     majority
    -0.77
     actually
    -0.76
     previously
    -0.75
    POSITIVE LOGITS
    ͝
    0.84
    èles
    0.84
     niks
    0.83
     muelle
    0.81
     contund
    0.80
     borer
    0.79
     कीजिए
    0.78
     changé
    0.78
    TypeId
    0.78
    كمة
    0.77
    Activations Density 0.003%

    No Known Activations