© 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. 109930
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    question phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
    tem
    0.46
    מ
    0.43
    Є
    0.43
     Perse
    0.42
    蓋
    0.41
     पुनर्
    0.41
    SE
    0.40
    盖
    0.40
    /
    0.39
    偪
    0.39
    POSITIVE LOGITS
     nascost
    0.48
     আমিও
    0.47
     hyvä
    0.45
     rivulet
    0.45
    私も
    0.45
     kys
    0.45
     rychle
    0.45
     reconhecimento
    0.44
     भयानक
    0.43
     accumulator
    0.43
    Activations Density 0.000%

    No Known Activations