© 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. 29068
    Prev
    Next
    INDEX
    Explanations

    run dev start scripts

    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
    Contains
    0.42
    xmlns
    0.39
    нения
    0.39
    惴
    0.38
    requires
    0.38
    includes
    0.37
     enthält
    0.37
    thirsty
    0.37
    益
    0.36
    contain
    0.35
    POSITIVE LOGITS
     pós
    0.47
     onderzoek
    0.43
     ambulance
    0.41
     furlough
    0.41
    amatkan
    0.40
     महसूस
    0.40
    akura
    0.39
     முதுகு
    0.38
     ice
    0.38
     неделю
    0.38
    Activations Density 0.002%

    No Known Activations