© 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. 81466
    Prev
    Next
    INDEX
    Explanations

    end of sentence or section metadata

    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
     teater
    -1.08
    umpulan
    -1.00
     grupp
    -0.98
    foglal
    -0.90
    ẩ
    -0.89
     emporio
    -0.88
     Meilleur
    -0.88
     Maak
    -0.87
    enumii
    -0.87
     Mentions
    -0.87
    POSITIVE LOGITS
     visitation
    1.35
     there
    1.33
    จะมี
    0.98
     espirituales
    0.98
    There
    0.94
     предвари
    0.94
     płasz
    0.93
     там
    0.90
    Visitation
    0.90
     Visitation
    0.89
    Activations Density 0.008%

    No Known Activations