© 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. 176851
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    Practical Good

    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
     vacun
    0.46
     poveć
    0.45
     Untold
    0.42
     вещей
    0.42
     Benefit
    0.42
     Freiheit
    0.42
    ≠
    0.41
     Differ
    0.40
     అంశ
    0.40
     Adv
    0.40
    POSITIVE LOGITS
    umann
    0.50
    我的
    0.47
    ках
    0.44
    ඛ
    0.44
    kh
    0.44
    klass
    0.44
    غرب
    0.43
    伯
    0.42
     männer
    0.42
    כּ
    0.42
    Activations Density 0.000%

    No Known Activations