© 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. 115519
    Prev
    Next
    INDEX
    Explanations

    injunctions and restraining orders

    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
    tetés
    -0.81
    ेद
    -0.73
    ikr
    -0.71
    viť
    -0.70
    Boc
    -0.70
     Kome
    -0.70
    ellidos
    -0.69
    蹉
    -0.69
    ージョン
    -0.69
    ellee
    -0.68
    POSITIVE LOGITS
     injunction
    3.88
     inj
    2.72
    inj
    2.41
     enjoined
    2.14
     enjo
    2.14
     restraining
    1.94
     restrain
    1.61
    junction
    1.48
     restrained
    1.44
     Restra
    1.39
    Activations Density 0.052%

    No Known Activations