© 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. 10-GEMMASCOPE-RES-131K
    7. 70390
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    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_10/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
     now
    -2.44
     for
    -2.33
     if
    -2.11
    ;
    -1.94
     this
    -1.94
     out
    -1.90
    If
    -1.84
     If
    -1.76
    by
    -1.75
     over
    -1.74
    POSITIVE LOGITS
    跸
    2.05
    ཫ
    1.86
    컹
    1.81
     dekol
    1.77
    ⍽
    1.77
    
    1.74
    Punkt
    1.71
    ޏ
    1.70
     peculiarly
    1.64
    ﹍﹍
    1.62
    Activations Density 0.200%

    No Known Activations