© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 60837
    Prev
    Next
    INDEX
    Explanations

    swap space management

    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
     ছাদে
    0.41
    묭
    0.41
     మేము
    0.41
     전체
    0.39
    ꉂ
    0.38
     parsing
    0.38
     победи
    0.37
     receptionist
    0.37
     joints
    0.37
    porter
    0.37
    POSITIVE LOGITS
     swap
    1.25
    swap
    1.19
     Swap
    1.16
    Swap
    1.11
     swaps
    1.11
     swapped
    0.98
     swapping
    0.97
    交换
    0.75
     intercamb
    0.64
    換
    0.63
    Activations Density 0.001%

    No Known Activations