© 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. 54334
    Prev
    Next
    INDEX
    Explanations

    DOM ancestor relationships

    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
    淥
    -1.20
     textu
    -1.13
     about
    -1.12
     แท้
    -1.12
    냑
    -1.01
     aumentare
    -1.00
     neceffary
    -0.99
     चाहिए
    -0.99
     Eindruck
    -0.98
     fufficient
    -0.98
    POSITIVE LOGITS
     afield
    0.94
    nologue
    0.93
    Ex
    0.93
     shabby
    0.93
    parent
    0.91
     vicinity
    0.91
     We
    0.91
    bliž
    0.89
     area
    0.88
     Our
    0.88
    Activations Density 0.003%

    No Known Activations