© 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. 180091
    Prev
    Next
    INDEX
    Explanations

    non-english words and technical terms

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

    Windows, 4, marketing, war

    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
     parrots
    0.49
     usur
    0.47
     parrot
    0.47
     solute
    0.46
     McMaster
    0.46
    ropshire
    0.45
     usurp
    0.45
    ={"
    0.45
     indoctr
    0.44
     sinister
    0.44
    POSITIVE LOGITS
     etmek
    0.49
    Dok
    0.48
    بعد
    0.47
     Effects
    0.47
     Teknologi
    0.47
    SH
    0.46
    Jakarta
    0.45
    Xia
    0.45
     பாதிக்கிறது
    0.44
    길
    0.44
    Activations Density 0.001%

    No Known Activations