© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2894
    Prev
    Next
    INDEX
    Explanations

    detailed information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ्स
    2.90
    th
    2.78
     личности
    2.70
     nello
    2.67
     leap
    2.48
    ll
    2.46
    泾
    2.45
    要想
    2.45
    ز
    2.37
    зыва
    2.36
    POSITIVE LOGITS
    et
    3.19
    ن
    3.12
     inlaid
    3.07
    স
    3.00
    an
    2.92
     детали
    2.82
    𝘻
    2.79
    ر
    2.69
    स
    2.67
    estens
    2.66
    Activations Density 0.463%

    No Known Activations