© 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. 54022
    Prev
    Next
    INDEX
    Explanations

    Questions and acronyms

    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
     []),
    -0.85
    Crust
    -0.80
     Temperatur
    -0.77
    énd
    -0.76
    委托
    -0.73
    унк
    -0.72
    dp
    -0.71
     बता
    -0.69
    保育園
    -0.68
     typically
    -0.68
    POSITIVE LOGITS
     MCI
    0.85
    MCI
    0.82
    mtl
    0.77
    Gens
    0.76
     NTA
    0.75
     NIH
    0.75
    neet
    0.74
    UDI
    0.73
     üblichen
    0.73
     хиру
    0.72
    Activations Density 0.007%

    No Known Activations