© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130998
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    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
    بيع
    -0.95
     Conférence
    -0.90
     either
    -0.90
    camion
    -0.86
    amanda
    -0.85
    uvres
    -0.85
    zeppelin
    -0.84
     Milán
    -0.83
    citet
    -0.83
    亦
    -0.83
    POSITIVE LOGITS
    anyahu
    0.97
    edoria
    0.94
    ut
    0.90
     '+':
    0.90
    URES
    0.87
    多的
    0.85
    IG
    0.85
     dads
    0.84
    UT
    0.84
    NT
    0.84
    Activations Density 0.010%

    No Known Activations