© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32684
    Prev
    Next
    INDEX
    Explanations

    Q&A formatGangs of Tooting Broadway

    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
    kerja
    -0.85
     zase
    -0.84
    Papers
    -0.83
     ieder
    -0.72
    몫
    -0.71
     Apenas
    -0.69
    logs
    -0.69
     EDIT
    -0.69
    Logs
    -0.69
     papers
    -0.69
    POSITIVE LOGITS
    нівер
    0.85
    歧
    0.82
    hiasan
    0.80
     eorum
    0.78
     esperaba
    0.76
    ulsions
    0.75
    ቹ
    0.74
     ää
    0.74
    称呼
    0.74
    atives
    0.73
    Activations Density 0.010%

    No Known Activations