© 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. 93722
    Prev
    Next
    INDEX
    Explanations

    days of the week and questions

    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
    ന്ന്
    -0.78
    死的
    -0.77
     Günther
    -0.74
     cử
    -0.73
     viewType
    -0.70
     dugout
    -0.69
     Norse
    -0.69
    学位
    -0.68
    FEA
    -0.68
    maline
    -0.68
    POSITIVE LOGITS
     slike
    0.79
    repe
    0.74
     reak
    0.72
     اهداف
    0.72
     darf
    0.72
     Reak
    0.71
    ﹪
    0.71
    ogens
    0.70
     kartu
    0.69
     keli
    0.69
    Activations Density 0.022%

    No Known Activations