© 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. 123922
    Prev
    Next
    INDEX
    Explanations

    God via Prophets

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

    people and foreign words

    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
    вной
    0.46
     refrigerator
    0.45
     microprocessor
    0.45
     keel
    0.43
     locks
    0.42
     FLOW
    0.42
     embossing
    0.42
     receipt
    0.41
    〽
    0.41
     contract
    0.41
    POSITIVE LOGITS
     людей
    0.50
    زا
    0.49
     ljudi
    0.47
     دهد
    0.46
     ľudí
    0.46
     കണ്ട
    0.45
     oamen
    0.45
     Verma
    0.44
     medzi
    0.44
     Naik
    0.44
    Activations Density 0.000%

    No Known Activations