© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108514
    Prev
    Next
    INDEX
    Explanations

    LOCAL paths and GHz bandwidths

    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
     on
    -0.93
     kategori
    -0.84
     category
    -0.83
    cazione
    -0.76
     分类
    -0.76
    
    -0.76
     生日
    -0.75
    ць
    -0.75
     Große
    -0.73
    bernador
    -0.72
    POSITIVE LOGITS
     project
    1.02
    
    0.91
     proj
    0.87
    stücks
    0.85
     énon
    0.83
    甩
    0.82
     plonge
    0.81
    
    0.80
    Project
    0.80
     infância
    0.80
    Activations Density 0.063%

    No Known Activations