© 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. 73306
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
     numerous
    -1.20
     publications
    -1.11
    :
    -1.06
    ;
    -1.03
     both
    -1.03
     Meksi
    -0.98
    PMID
    -0.97
     but
    -0.95
     descrito
    -0.94
    っており
    -0.93
    POSITIVE LOGITS
     даже
    1.25
    Tanggal
    1.20
    January
    1.15
    September
    1.13
    October
    1.10
     January
    1.10
    February
    1.06
    ÍTULO
    1.04
    îner
    1.02
    ()}
    0.99
    Activations Density 0.503%

    No Known Activations