© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115889
    Prev
    Next
    INDEX
    Explanations

    Names followed by surnames

    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
     ய
    -0.81
     erm
    -0.71
    坊
    -0.69
     grà
    -0.68
     presided
    -0.66
     затем
    -0.66
    夾
    -0.65
    Без
    -0.65
     lạt
    -0.64
     then
    -0.64
    POSITIVE LOGITS
     actualidad
    0.87
    OTES
    0.81
    žu
    0.79
     Vedic
    0.78
    bben
    0.77
     bewegen
    0.76
     før
    0.75
     conçus
    0.74
     omkring
    0.74
     Milla
    0.74
    Activations Density 0.048%

    No Known Activations