© 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. 90218
    Prev
    Next
    INDEX
    Explanations

    legal complaint alleges

    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
    ágen
    -0.81
     Hubert
    -0.79
    錮
    -0.79
    忧
    -0.78
     البيت
    -0.75
     части
    -0.75
     المكان
    -0.73
     penalty
    -0.72
     شهاد
    -0.72
     preventive
    -0.71
    POSITIVE LOGITS
     complaint
    1.14
     plau
    1.13
     pleads
    1.09
     allege
    0.96
     allegations
    0.95
     pleaded
    0.91
     pleading
    0.91
     alleges
    0.91
     reple
    0.90
     alleging
    0.90
    Activations Density 0.019%

    No Known Activations