© 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. 211652
    Prev
    Next
    INDEX
    Explanations

    training, product, Trump, operating

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

    waste resources investigating

    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
    这件事
    0.45
    Antib
    0.44
    yg
    0.43
    ອງ
    0.42
    these
    0.42
    ukh
    0.41
    util
    0.40
    [][]
    0.40
    랗
    0.39
    Utility
    0.38
    POSITIVE LOGITS
     senha
    0.48
    }=(-
    0.46
     supremo
    0.46
     assass
    0.45
     código
    0.45
     Geheim
    0.44
     tarih
    0.43
     nhìn
    0.43
     guerra
    0.43
     geist
    0.43
    Activations Density 0.001%

    No Known Activations