© 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. 102639
    Prev
    Next
    INDEX
    Explanations

    Japanese and Korean names

    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
     actuel
    -0.72
     wipe
    -0.71
     jeżeli
    -0.71
    lijkse
    -0.68
     semel
    -0.67
     logarithmic
    -0.66
     alguma
    -0.66
     xícara
    -0.66
    rateful
    -0.66
    Basics
    -0.66
    POSITIVE LOGITS
    ამ
    0.77
    beam
    0.71
    ancien
    0.70
     regola
    0.68
     Micros
    0.68
     destacar
    0.68
     boon
    0.68
     dams
    0.68
     motives
    0.68
     Bono
    0.68
    Activations Density 0.019%

    No Known Activations