© 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. 5297
    Prev
    Next
    INDEX
    Explanations

    pulled back

    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
     ►
    0.73
     PQ
    0.71
     चुंबकीय
    0.69
     [(
    0.66
    .]
    0.65
    ↵
    0.65
     quartz
    0.65
    ตุ
    0.64
     electrodes
    0.64
     √
    0.63
    POSITIVE LOGITS
     mỹ
    0.81
     السعود
    0.81
     الثانيه
    0.79
    إن
    0.79
    onesia
    0.77
     إن
    0.77
     нём
    0.76
    گیرد
    0.76
     sein
    0.76
    韵
    0.75
    Activations Density 0.002%

    No Known Activations