© 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. 76199
    Prev
    Next
    INDEX
    Explanations

    setting states or values

    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
     اضافه
    -0.89
    addView
    -0.88
    érable
    -0.86
    vements
    -0.83
    addCell
    -0.82
    tieron
    -0.82
     Rashford
    -0.82
    𝚣
    -0.82
     добавля
    -0.81
    toler
    -0.79
    POSITIVE LOGITS
     set
    4.47
     setting
    2.94
    set
    2.70
    设置为
    2.66
     Set
    2.45
     ustaw
    2.30
    Set
    2.25
    設定
    2.22
    设置
    2.20
     sets
    2.19
    Activations Density 0.172%

    No Known Activations