© 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. 118005
    Prev
    Next
    INDEX
    Explanations

    published Disposition, published opinion

    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
    舛
    -0.69
     است
    -0.69
     सकता
    -0.69
    殿
    -0.68
    蜴
    -0.67
    omores
    -0.67
    Berry
    -0.67
     FIFO
    -0.66
    thalene
    -0.66
     vga
    -0.66
    POSITIVE LOGITS
    ambil
    0.77
     Vorgang
    0.71
    Seattle
    0.71
     coloque
    0.70
    intens
    0.69
     messen
    0.69
    äder
    0.67
    ading
    0.67
    curios
    0.66
    Í
    0.66
    Activations Density 0.036%

    No Known Activations