© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14250
    Prev
    Next
    INDEX
    Explanations

    businesses and services

    np_acts-logits-general · gemini-2.5-flash-lite

    user questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cleanest
    0.50
    K
    0.49
    িজ
    0.48
     Box
    0.47
    Π
    0.45
    目标
    0.45
    Tras
    0.45
    S
    0.44
     RIM
    0.44
    ມັນ
    0.43
    POSITIVE LOGITS
     ใช่
    0.50
     医学
    0.49
    менение
    0.47
     léč
    0.46
    sigmoid
    0.46
     Сасик
    0.46
     가수
    0.46
    gester
    0.44
    onycha
    0.44
     असह
    0.44
    Activations Density 0.001%

    No Known Activations