© 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. 83273
    Prev
    Next
    INDEX
    Explanations

    realize unreal gains

    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
    usiness
    -0.75
    สง
    -0.74
    wiec
    -0.71
     Volumes
    -0.70
    ahkan
    -0.69
    🪂
    -0.68
    ♌
    -0.68
     atrás
    -0.68
    mence
    -0.67
    eaux
    -0.67
    POSITIVE LOGITS
     unreal
    3.22
     realized
    2.36
     Unreal
    2.34
    Unreal
    2.30
     realised
    2.13
     unre
    1.70
    unre
    1.46
     realize
    1.37
     реали
    1.37
     gains
    1.35
    Activations Density 0.032%

    No Known Activations