© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189735
    Prev
    Next
    INDEX
    Explanations

    foreign words and business deals

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

    AI assistance and generation tools

    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_262k_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
     x
    0.41
     type
    0.38
     water
    0.38
     run
    0.37
     veggies
    0.37
     ultra
    0.36
     build
    0.35
     path
    0.35
     pathway
    0.35
    0.35
    POSITIVE LOGITS
    א
    0.46
    את
    0.45
    мета
    0.45
    ๗
    0.45
    אי
    0.44
    интере
    0.43
    ում
    0.43
    ingresso
    0.43
    𝗱
    0.43
    Გ
    0.43
    Activations Density 0.112%

    No Known Activations