© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5405
    Prev
    Next
    INDEX
    Explanations

    terminal or command prompt

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     که
    0.91
    正则
    0.88
    の
    0.81
     bude
    0.77
    inskii
    0.76
    的這個
    0.76
    นี้
    0.75
    id
    0.73
     saham
    0.72
     žena
    0.72
    POSITIVE LOGITS
     Relatively
    0.84
    tj
    0.80
     relatively
    0.80
     hundreds
    0.75
     Sharp
    0.74
    relatively
    0.72
     Highly
    0.69
    ృ
    0.69
     Hundreds
    0.69
     Adopt
    0.69
    Activations Density 0.004%

    No Known Activations