© 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. 45471
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming attributes

    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
     شوهر
    -0.73
     интел
    -0.70
    网页
    -0.67
    Stop
    -0.64
    態度
    -0.61
    days
    -0.60
     routinely
    -0.60
     agradable
    -0.59
    ALLOW
    -0.59
     generations
    -0.59
    POSITIVE LOGITS
    music
    0.68
    LEI
    0.67
    qualities
    0.67
    戡
    0.66
    kez
    0.65
     confer
    0.65
     entrar
    0.63
     abnormalities
    0.62
     Confer
    0.60
     gardeners
    0.60
    Activations Density 0.073%

    No Known Activations