© 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. 34-GEMMASCOPE-RES-131K
    7. 84853
    Prev
    Next
    INDEX
    Explanations

    titles, dates, and topics

    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
     Friday
    -0.93
     Wednesday
    -0.83
     coronal
    -0.80
    釣り
    -0.80
     Thursday
    -0.77
     Audible
    -0.77
    Puri
    -0.77
     Viceroy
    -0.74
     nativity
    -0.72
     Boating
    -0.72
    POSITIVE LOGITS
     Га
    0.91
    
    0.91
    ěř
    0.88
    issé
    0.85
     maal
    0.84
    вят
    0.82
    ſer
    0.82
    więks
    0.81
    zaak
    0.81
    
    0.81
    Activations Density 0.001%

    No Known Activations