© 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. 34-GEMMASCOPE-RES-131K
    7. 73582
    Prev
    Next
    INDEX
    Explanations

    ASP.NET DropDownList C#

    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_34/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
     francia
    -1.15
    
    -1.09
     illet
    -1.06
     Gouver
    -1.05
     tanggal
    -1.03
    ໋
    -1.03
     vertus
    -1.02
    |--
    -1.01
    слен
    -1.01
     työ
    -1.01
    POSITIVE LOGITS
     betreffenden
    1.32
    jenige
    1.14
     erforder
    1.05
     erwähnten
    1.03
    k
    1.02
    on
    1.00
     Enables
    0.99
     erforderlichen
    0.99
     Hauses
    0.98
     instead
    0.97
    Activations Density 0.001%

    No Known Activations