© 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. 33282
    Prev
    Next
    INDEX
    Explanations

    naming convention

    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
     /\.(
    -0.96
     doubted
    -0.84
    tsz
    -0.83
    blurRadius
    -0.80
     działalności
    -0.77
    تیاز
    -0.76
    yttä
    -0.76
     形
    -0.76
    ñora
    -0.75
     Erfolgs
    -0.75
    POSITIVE LOGITS
     convention
    4.66
     conventions
    4.06
    convention
    3.63
     Convention
    3.03
    Convention
    3.02
     Conventions
    2.88
    conven
    2.72
    Conven
    2.61
     conven
    2.09
    约定
    1.98
    Activations Density 0.124%

    No Known Activations