© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5571
    Prev
    Next
    INDEX
    Explanations

    Go code for data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    工作
    0.67
     mối
    0.65
    works
    0.65
    侣
    0.61
    ラム
    0.60
     સમા
    0.59
    ut
    0.59
    oda
    0.58
    末
    0.58
    appro
    0.57
    POSITIVE LOGITS
     Filipino
    0.89
     Philippines
    0.86
     Quezon
    0.83
     Filipinos
    0.82
    Philippines
    0.80
     Epilepsy
    0.79
     Barangay
    0.79
     Filip
    0.78
    ([]
    0.78
    LAGAB
    0.78
    Activations Density 0.040%

    No Known Activations