© 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. 2863
    Prev
    Next
    INDEX
    Explanations

    horizon, reward

    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
    م
    5.00
    ا
    4.49
    ੀ
    4.22
     비롯
    3.49
    y
    3.42
    ্স
    3.39
    ्स
    3.38
    й
    3.36
    ی
    3.15
    یی
    3.12
    POSITIVE LOGITS
    ن
    4.60
    లో
    3.65
    QtWidgets
    3.35
     bont
    3.31
    های
    3.10
    மான
    2.97
    ें
    2.97
    ст
    2.96
    ют
    2.85
    с
    2.84
    Activations Density 0.298%

    No Known Activations