© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 48103
    Prev
    Next
    INDEX
    Explanations

    betting whether on or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fancied
    0.37
     cuộc
    0.37
     edging
    0.37
    >∕</
    0.37
     plagued
    0.36
     Nicki
    0.36
     discounted
    0.36
     flirting
    0.36
    꽤
    0.36
    ϭ
    0.36
    POSITIVE LOGITS
     ব্যবহারের
    0.40
    diss
    0.39
    දර
    0.39
    anneer
    0.38
     comply
    0.37
     satisfy
    0.37
     ব্যবহারে
    0.37
    夷
    0.36
     decompose
    0.36
    婁
    0.35
    Activations Density 0.012%

    No Known Activations