© 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. 102504
    Prev
    Next
    INDEX
    Explanations

    programming class names

    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
     State
    -0.80
     system
    -0.74
     cercando
    -0.71
     ofrecen
    -0.71
     decisions
    -0.66
    methyl
    -0.66
     Begriffe
    -0.66
     diu
    -0.66
     Type
    -0.66
     splitting
    -0.66
    POSITIVE LOGITS
    atterson
    0.86
    tft
    0.76
    nikova
    0.75
     validators
    0.74
    Doppel
    0.74
     viceversa
    0.73
    Servers
    0.73
     eneste
    0.72
     prefect
    0.72
     hø
    0.72
    Activations Density 0.018%

    No Known Activations