© 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. 176783
    Prev
    Next
    INDEX
    Explanations

    phrases that modify or follow

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

    locations, states, possessions, or durations

    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
    t
    0.52
    只是
    0.44
     that
    0.42
    ｔ
    0.41
     reff
    0.41
    Ｔ
    0.40
     everytime
    0.40
     equipped
    0.39
     which
    0.39
    的时候
    0.39
    POSITIVE LOGITS
     Polaribacter
    0.53
    எம்
    0.48
    7
    0.47
     miei
    0.47
    5
    0.46
     desafío
    0.45
     headwinds
    0.45
    aguars
    0.45
     meines
    0.45
     desafíos
    0.45
    Activations Density 0.002%

    No Known Activations