© 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. 76356
    Prev
    Next
    INDEX
    Explanations

    syntax errors or variables

    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
    lands
    -0.86
    égorie
    -0.84
    軋
    -0.84
    凪
    -0.77
     you
    -0.77
    geot
    -0.77
     Kn
    -0.76
    ⚡️
    -0.75
     soon
    -0.75
    digital
    -0.74
    POSITIVE LOGITS
     Briefe
    0.96
    THROUGH
    0.95
     isShow
    0.85
     uova
    0.84
     Nutz
    0.81
     servlet
    0.80
    去年
    0.80
     scarpe
    0.79
     نوز
    0.79
    Bahn
    0.78
    Activations Density 0.000%

    No Known Activations