© 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. 430
    Prev
    Next
    INDEX
    Explanations

    plane or planar contexts

    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
     forlorn
    -0.94
     emplea
    -0.93
     téměř
    -0.86
    噌
    -0.85
     poign
    -0.85
    沵
    -0.84
     unchanging
    -0.82
     exasper
    -0.79
     sedu
    -0.78
    νες
    -0.78
    POSITIVE LOGITS
    toid
    1.60
     jane
    1.05
    Гру
    1.00
    Jane
    0.99
     Jane
    0.97
     mudah
    0.96
    曲目
    0.95
     kebutuhan
    0.92
    パー
    0.90
     еды
    0.88
    Activations Density 0.029%

    No Known Activations