© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39210
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or conditions

    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
     pérd
    -1.56
     siè
    -1.48
    鳚
    -1.38
     绘画
    -1.38
     parlant
    -1.37
     acheter
    -1.35
     我的
    -1.35
     pourraient
    -1.35
     própri
    -1.34
    だけではなく
    -1.34
    POSITIVE LOGITS
     or
    2.48
     first
    1.72
     new
    1.55
     no
    1.43
     without
    1.42
    或
    1.42
     through
    1.38
     или
    1.36
     time
    1.35
     when
    1.34
    Activations Density 0.029%

    No Known Activations