© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116727
    Prev
    Next
    INDEX
    Explanations

    assembly registers and hexadecimal

    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
     spel
    -0.79
     Шо
    -0.79
    ティスト
    -0.77
     гр
    -0.77
    WTS
    -0.76
     Draht
    -0.75
    ведите
    -0.74
    uther
    -0.73
    さな
    -0.73
    是什么意思
    -0.73
    POSITIVE LOGITS
     unabhängig
    0.80
    oline
    0.78
    ноза
    0.77
     offensichtlich
    0.75
     solcher
    0.75
    opponent
    0.75
     bürger
    0.74
     zombies
    0.73
    ILog
    0.73
    cije
    0.72
    Activations Density 0.002%

    No Known Activations