© 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-262K
    7. 17080
    Prev
    Next
    INDEX
    Explanations

    between two

    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_262k_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
    am
    0.87
    ד
    0.79
     друг
    0.70
    स
    0.70
    in
    0.67
    на
    0.64
    nicht
    0.63
    सँग
    0.63
     probleme
    0.62
    explique
    0.60
    POSITIVE LOGITS
     pilgrims
    0.61
     R
    0.60
     notebooks
    0.57
    ì
    0.57
    此类
    0.55
     Journalists
    0.54
     T
    0.54
     glaciers
    0.54
     segala
    0.54
     college
    0.53
    Activations Density 0.047%

    No Known Activations