© 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. 34-GEMMASCOPE-RES-131K
    4. 23597
    Prev
    Next
    INDEX
    Explanations

    using System

    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
    "))
    -0.88
    innung
    -0.88
     bereits
    -0.86
    Cum
    -0.81
     at
    -0.79
     kezel
    -0.79
     Nutz
    -0.79
    "}}
    -0.79
    Fili
    -0.78
     نح
    -0.78
    POSITIVE LOGITS
     correc
    0.87
     whoa
    0.85
     Sitio
    0.83
     ANA
    0.83
     ähnlichen
    0.81
    DNEY
    0.80
     DAZ
    0.80
     OND
    0.79
     ähnliche
    0.79
     simpl
    0.79
    Activations Density 0.010%

    No Known Activations