© 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. 119094
    Prev
    Next
    INDEX
    Explanations

    style and UI elements

    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
     unteren
    -0.81
    暧
    -0.74
    HashSet
    -0.74
     capabilities
    -0.73
    prem
    -0.73
     płyn
    -0.72
    最初は
    -0.72
     reef
    -0.71
     breiten
    -0.70
    当時は
    -0.69
    POSITIVE LOGITS
    FlatStyle
    1.13
    BorderStyle
    1.02
     style
    1.00
    FontStyle
    0.88
     stylu
    0.87
     STYLE
    0.86
     Geologist
    0.85
    fontStyle
    0.84
    estyle
    0.84
     TextStyle
    0.83
    Activations Density 0.001%

    No Known Activations