© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83321
    Prev
    Next
    INDEX
    Explanations

    al- and ma'- prefixes

    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
    節約
    -0.80
    šení
    -0.75
    这篇
    -0.71
    約束
    -0.70
    enne
    -0.70
    Successful
    -0.69
     enthusiastic
    -0.68
     во
    -0.68
    交叉
    -0.68
    过去的
    -0.66
    POSITIVE LOGITS
    ことができました
    0.87
    ことができ
    0.82
     rękaw
    0.81
    一听
    0.79
    interess
    0.79
    づけ
    0.78
    様が
    0.76
    afar
    0.76
     towards
    0.76
    ribu
    0.75
    Activations Density 0.005%

    No Known Activations