© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    CSS for Styling

    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
    ため
    3.43
    म
    3.40
    й
    3.29
     gameObject
    3.05
     reins
    2.92
    ী
    2.84
    os
    2.77
     ductility
    2.77
     boli
    2.69
    alış
    2.68
    POSITIVE LOGITS
    ّه
    2.89
    𝒈
    2.80
    𝓊
    2.78
    েই
    2.76
    offsetX
    2.73
    𝒂
    2.73
    ۥ
    2.70
    𝓌
    2.68
     lư
    2.59
     manageable
    2.59
    Activations Density 0.273%

    No Known Activations