© 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. 115468
    Prev
    Next
    INDEX
    Explanations

    runtime environment

    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
    蜍
    -0.95
     usurp
    -0.89
    品的
    -0.89
    場所に
    -0.87
     dijeron
    -0.87
     distanza
    -0.87
     renang
    -0.85
    chnet
    -0.85
    怎样的
    -0.84
     repudi
    -0.82
    POSITIVE LOGITS
     environment
    1.18
     Environment
    1.16
    环境
    1.05
    environment
    1.02
    Environment
    1.01
    阁
    0.96
     Came
    0.94
    VIRON
    0.91
    inale
    0.91
     beträgt
    0.89
    Activations Density 0.012%

    No Known Activations