© 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. 10-GEMMASCOPE-RES-131K
    4. 84994
    Prev
    Next
    INDEX
    Explanations

    states, countries, and regions

    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_10/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
     from
    -1.74
     to
    -1.67
     that
    -1.32
    饪
    -1.30
     climático
    -1.17
     ندار
    -1.16
     there
    -1.11
     first
    -1.09
     for
    -1.09
    eably
    -1.05
    POSITIVE LOGITS
     my
    1.31
     soluciones
    1.30
    我们的
    1.30
     wciąż
    1.27
    lateur
    1.24
    
    1.22
    vieren
    1.22
    mados
    1.21
    quelize
    1.21
    <bos>
    1.21
    Activations Density 0.609%

    No Known Activations