© 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. 6857
    Prev
    Next
    INDEX
    Explanations

    court cases and code

    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
    ར་བ
    -0.75
     لیگ
    -0.74
    electrons
    -0.70
    mbi
    -0.69
     Bloch
    -0.68
    ัส
    -0.68
     cé
    -0.67
    ontent
    -0.67
     Allocate
    -0.67
    材
    -0.67
    POSITIVE LOGITS
     Advance
    0.66
    期間
    0.65
     непри
    0.65
     Riga
    0.63
    kshake
    0.63
    dispon
    0.63
    hedron
    0.62
    颜
    0.61
     judul
    0.61
     estrella
    0.61
    Activations Density 0.056%

    No Known Activations