© 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. 98013
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
     hilfiger
    -0.82
    永遠
    -0.81
    ليد
    -0.80
    Jereo
    -0.79
     económica
    -0.75
     хочется
    -0.74
    érez
    -0.73
     investigação
    -0.71
    uary
    -0.70
     kjem
    -0.70
    POSITIVE LOGITS
    sten
    0.82
    Serge
    0.81
     live
    0.74
     glycine
    0.73
     HDF
    0.73
     inference
    0.73
     HEC
    0.72
    śle
    0.71
     priming
    0.70
     ((!
    0.70
    Activations Density 0.001%

    No Known Activations