© 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. 22-GEMMASCOPE-RES-131K
    4. 35980
    Prev
    Next
    INDEX
    Explanations

    accepting or embracing something

    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_22/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
    =
    -1.05
    //
    -0.97
    ↵↵↵
    -0.96
     frambo
    -0.96
    last
    -0.96
         
    -0.96
    
    -0.95
    ↵↵↵↵↵
    -0.94
     such
    -0.93
     действие
    -0.93
    POSITIVE LOGITS
     that
    1.34
     التي
    1.27
     posibilidades
    1.20
     facilitators
    1.19
     accept
    1.18
     invitaciones
    1.17
     Accept
    1.16
     what
    1.16
    bagian
    1.16
     pequeñas
    1.16
    Activations Density 0.017%

    No Known Activations