© 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. 66603
    Prev
    Next
    INDEX
    Explanations

    costs and negative outcomes

    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
     Deficiency
    -0.79
     lacking
    -0.79
     alcoholism
    -0.75
    cimentos
    -0.75
     inadequacy
    -0.74
    licitations
    -0.73
     bestä
    -0.73
     Alkohol
    -0.73
     memperoleh
    -0.72
    няются
    -0.71
    POSITIVE LOGITS
     cost
    1.38
     costs
    1.23
    COST
    1.13
    costs
    1.09
    cost
    1.09
    Cost
    0.98
    副作用
    0.98
     Cost
    0.95
     COST
    0.93
     kosz
    0.93
    Activations Density 0.168%

    No Known Activations