© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82845
    Prev
    Next
    INDEX
    Explanations

    rescue mission, highest mountains

    np_acts-logits-general · gemini-2.5-flash-lite

    tuple packing and unpacking, interprets commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sáng
    0.48
     Público
    0.46
    彻底
    0.45
     biti
    0.45
    ;">
    0.44
    的数量
    0.44
     Seong
    0.43
    z
    0.43
     Takashi
    0.42
    ාල
    0.42
    POSITIVE LOGITS
    Backed
    0.46
    csim
    0.45
    су
    0.44
     암
    0.44
    Edwards
    0.44
    垟
    0.44
     வாய்
    0.43
    replay
    0.43
    NOTES
    0.42
    шении
    0.42
    Activations Density 0.001%

    No Known Activations