© 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. 147412
    Prev
    Next
    INDEX
    Explanations

    punishes builds or your usual

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

    GG alleles

    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
     durchaus
    0.48
    を得
    0.48
     innumerable
    0.43
    또한
    0.42
     bhavati
    0.41
    記入
    0.41
    त्ति
    0.40
    믈
    0.40
     supremely
    0.40
    ственности
    0.40
    POSITIVE LOGITS
    နဲ့
    0.48
    向けの
    0.48
     ও
    0.47
     Airbnb
    0.46
     ভারী
    0.45
     +
    0.45
     snacking
    0.44
     backpack
    0.43
     backpacking
    0.43
     kvůli
    0.43
    Activations Density 0.001%

    No Known Activations