© 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. 34540
    Prev
    Next
    INDEX
    Explanations

    absence, permission, or comment

    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
    doc
    -0.89
    Beautiful
    -0.85
    W
    -0.84
    s
    -0.82
    べる
    -0.81
    clamp
    -0.81
     delimit
    -0.81
    tir
    -0.80
    ti
    -0.79
    見た
    -0.79
    POSITIVE LOGITS
     stripping
    1.00
    
    0.96
    さんも
    0.95
    opcional
    0.91
    diseño
    0.91
    casco
    0.90
     resalt
    0.88
    ОТ
    0.88
     estri
    0.88
    pompa
    0.87
    Activations Density 0.010%

    No Known Activations