© 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. 66389
    Prev
    Next
    INDEX
    Explanations

    ons, on, Mons, Son

    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
     Austausch
    -0.75
    Ω
    -0.74
    endless
    -0.70
     disruption
    -0.68
    tiska
    -0.67
    comfortable
    -0.66
     tent
    -0.66
     defy
    -0.66
    magazin
    -0.65
     yard
    -0.65
    POSITIVE LOGITS
    ología
    0.78
    ensk
    0.76
    học
    0.75
     Oleh
    0.73
     JPL
    0.73
    echa
    0.73
     য
    0.71
    findViewById
    0.71
    igo
    0.69
    ícula
    0.69
    Activations Density 0.030%

    No Known Activations