© 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. 16-GEMMASCOPE-2-RES-16K
    7. 851
    Prev
    Next
    INDEX
    Explanations

    rooms and their contents

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

    rooms and bedrooms

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    '
    1.08
    c
    0.80
     delet
    0.70
    븅
    0.68
    に見
    0.63
    ם
    0.63
    쩡
    0.61
    ̌
    0.61
    Го
    0.60
    喬
    0.60
    POSITIVE LOGITS
     ROOM
    0.98
    ला
    0.90
    ло
    0.89
     room
    0.89
    те
    0.89
     комнаты
    0.88
     rooms
    0.87
    at
    0.84
    rooms
    0.82
    room
    0.81
    Activations Density 0.497%

    No Known Activations