© 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. 22-GEMMASCOPE-RES-131K
    7. 84136
    Prev
    Next
    INDEX
    Explanations

    specified number

    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_22/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
     Grüßen
    -1.02
    maktadır
    -0.97
    köp
    -0.96
    ucap
    -0.95
     män
    -0.95
    häng
    -0.93
     سینم
    -0.91
     kotor
    -0.91
     considérer
    -0.90
    rechten
    -0.89
    POSITIVE LOGITS
     duradero
    1.22
    了不少
    1.00
    了什么
    0.99
     cheio
    0.95
    サク
    0.94
     evtl
    0.92
    dillera
    0.91
    du
    0.91
     TUN
    0.90
    long
    0.89
    Activations Density 0.001%

    No Known Activations