© 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. 28422
    Prev
    Next
    INDEX
    Explanations

    numbers after names

    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
     terdekat
    -1.03
     only
    -1.00
     Nguy
    -0.98
    rangea
    -0.96
    仕上が
    -0.94
     its
    -0.94
    
    -0.93
     Qaraldi
    -0.91
    mox
    -0.90
    大正
    -0.90
    POSITIVE LOGITS
    了许多
    0.99
    了很多
    0.97
    v
    0.94
    1
    0.94
    r
    0.94
    了不少
    0.93
    7
    0.91
    l
    0.91
    了些
    0.90
     liefern
    0.89
    Activations Density 0.002%

    No Known Activations