© 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. 116795
    Prev
    Next
    INDEX
    Explanations

    typed definitions appearing after commands

    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
    第一次
    -0.73
    avice
    -0.70
    Exceeded
    -0.69
     Adonis
    -0.67
    objectId
    -0.66
    tolo
    -0.66
     ofs
    -0.65
    heir
    -0.65
     Fraser
    -0.63
     tropicales
    -0.63
    POSITIVE LOGITS
    bsp
    0.73
    genos
    0.71
    puestas
    0.70
     fragmentos
    0.69
     מוצ
    0.69
     ポケモン
    0.68
    NESOTA
    0.67
    cting
    0.66
    Job
    0.65
    woch
    0.65
    Activations Density 0.068%

    No Known Activations