© 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. 10-GEMMASCOPE-RES-131K
    7. 80827
    Prev
    Next
    INDEX
    Explanations

    code elements and specific phrases

    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
     because
    -1.52
     when
    -1.36
     gdyż
    -1.27
     despite
    -1.23
     their
    -1.23
    しますが
    -1.21
    しちゃ
    -1.16
    其余
    -1.16
    bershka
    -1.15
     потому
    -1.14
    POSITIVE LOGITS
    ↵
    1.55
     også
    1.41
    \}}
    1.41
     Secrétaire
    1.41
    pendente
    1.41
    
    1.32
     destinée
    1.30
    </sup>
    1.30
    μων
    1.30
     azienda
    1.29
    Activations Density 0.000%

    No Known Activations