© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119129
    Prev
    Next
    INDEX
    Explanations

    learning and facts

    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_40_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
    不等
    0.43
    []}
    0.38
     róż
    0.37
     আকাশে
    0.37
     ['
    0.37
    neq
    0.37
     immers
    0.37
    位
    0.37
     stabilizers
    0.36
     unequal
    0.36
    POSITIVE LOGITS
    propoxy
    0.45
    xcuser
    0.41
     Sudah
    0.40
    लट
    0.40
     martyr
    0.39
    Fetching
    0.39
    govor
    0.39
     नाबाल
    0.39
     femmes
    0.38
     женой
    0.38
    Activations Density 0.002%

    No Known Activations