© 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. 118479
    Prev
    Next
    INDEX
    Explanations

    condition or race condition

    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
    oas
    -0.79
    imentos
    -0.76
    raire
    -0.74
    melten
    -0.73
    gelegen
    -0.72
     wearer
    -0.72
    ؒ
    -0.71
     vientre
    -0.71
    見た目
    -0.70
     PSM
    -0.69
    POSITIVE LOGITS
     condition
    5.72
    condition
    4.84
     Condition
    4.66
    Condition
    4.56
     conditions
    4.34
    条件
    4.06
     CONDITION
    3.75
    CONDITION
    3.67
     Conditions
    3.56
     condición
    3.55
    Activations Density 0.147%

    No Known Activations