© 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. 22-GEMMASCOPE-RES-131K
    7. 28494
    Prev
    Next
    INDEX
    Explanations

    when subject follows

    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_22/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
    ården
    -1.02
     has
    -0.95
    随之
    -0.93
    共产
    -0.93
    wnątrz
    -0.93
    有两个
    -0.92
    紧接着
    -0.88
    嗽
    -0.87
    やか
    -0.86
     okresie
    -0.86
    POSITIVE LOGITS
     this
    1.38
     основные
    1.02
    Iné
    0.95
    這
    0.94
    ∖
    0.93
     they
    0.93
     these
    0.91
     好き
    0.91
    ACHED
    0.91
    ٕ
    0.90
    Activations Density 0.025%

    No Known Activations