© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33407
    Prev
    Next
    INDEX
    Explanations

    doubling time

    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_all/layer_41_width_262k_l0_big
    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
    irmer
    0.42
    र्देश
    0.39
     hộ
    0.38
     hooded
    0.38
     verhindert
    0.38
     $(`.
    0.38
     alloy
    0.37
     EXISTS
    0.37
     verão
    0.36
    荽
    0.36
    POSITIVE LOGITS
     doubling
    2.66
     doubled
    2.09
    Dou
    1.95
    dou
    1.91
     Dou
    1.90
     doubles
    1.89
     dou
    1.88
     Doubles
    1.66
     DOU
    1.65
     doubl
    1.40
    Activations Density 0.003%

    No Known Activations