© 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. 19404
    Prev
    Next
    INDEX
    Explanations

    president statements

    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
     them
    -1.36
     kablo
    -1.33
    ;&
    -1.26
     vogliono
    -1.26
     kollu
    -1.23
    ?”
    -1.23
    遢
    -1.22
     撮っ
    -1.20
    銪
    -1.17
     stund
    -1.16
    POSITIVE LOGITS
     to
    2.05
    𝑅
    1.70
    ikusbot
    1.65
    ৢ
    1.48
    
    1.48
    $--
    1.46
    EdgeInsets
    1.43
     obrázok
    1.40
     이미
    1.40
    sữa
    1.39
    Activations Density 0.027%

    No Known Activations