© 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. 25884
    Prev
    Next
    INDEX
    Explanations

    international footballers and RAC

    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
     PERIOD
    -0.68
    ReadByte
    -0.66
    PERIOD
    -0.66
     Periodic
    -0.65
     PETERS
    -0.65
    walk
    -0.65
    вающие
    -0.65
    霸
    -0.64
     Indigo
    -0.64
     Peters
    -0.63
    POSITIVE LOGITS
     británica
    0.73
    racite
    0.73
     clay
    0.72
    仓
    0.71
    ං
    0.69
    avoit
    0.68
    lact
    0.68
     scape
    0.68
     Kolo
    0.68
     arg
    0.67
    Activations Density 0.091%

    No Known Activations