© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    something or somewhere

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

    something or someone

    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
    헷
    0.57
     layoffs
    0.55
    only
    0.54
     sempat
    0.53
    so
    0.52
     quienes
    0.52
    kond
    0.52
    𝖎
    0.52
    a
    0.51
    icono
    0.51
    POSITIVE LOGITS
    Something
    0.75
     quelque
    0.73
     algún
    0.72
     algum
    0.70
    뭔
    0.68
     somewhere
    0.67
     quelqu
    0.67
     qualcosa
    0.66
     valam
    0.66
     alguma
    0.66
    Activations Density 0.231%

    No Known Activations