© 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. 87125
    Prev
    Next
    INDEX
    Explanations

    Our followed by a word

    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
     surnames
    -0.80
    Rojo
    -0.75
    鏡頭
    -0.74
     Intervals
    -0.72
     names
    -0.72
    我们就
    -0.72
    出来ました
    -0.69
     employers
    -0.68
     by
    -0.68
     Gaps
    -0.68
    POSITIVE LOGITS
    ｒ
    0.89
    多吃
    0.82
     milyon
    0.82
    ığı
    0.81
    Picker
    0.80
     systeem
    0.80
     hObject
    0.79
     sistema
    0.78
    ºC
    0.78
     丹
    0.77
    Activations Density 0.013%

    No Known Activations