© 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. 25728
    Prev
    Next
    INDEX
    Explanations

    public method or class declaration

    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
     長袖
    -0.96
     rotina
    -0.95
     коммуника
    -0.90
     feitas
    -0.89
     AdapterView
    -0.87
     now
    -0.87
    
    -0.87
     acessórios
    -0.85
    攥
    -0.85
    executed
    -0.85
    POSITIVE LOGITS
     того
    0.91
     or
    0.91
     auch
    0.90
     with
    0.89
     también
    0.87
     kebanyakan
    0.86
    However
    0.86
     same
    0.85
     также
    0.85
     you
    0.84
    Activations Density 0.010%

    No Known Activations