© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1923
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pihaknya
    0.87
    琀
    0.75
    そらく
    0.74
    ائیں۔
    0.72
    SuspendLayout
    0.72
     మాట్లాడుతూ
    0.65
     açısından
    0.64
    ందన్నారు
    0.63
    ancı
    0.63
    pexels
    0.61
    POSITIVE LOGITS
    !
    5.34
    !!
    4.70
    ！
    4.68
     !
    4.50
    !!!
    4.50
    !"
    4.44
    !)
    4.41
    !”
    4.38
    !!!!
    4.26
    !).
    4.22
    Activations Density 1.580%

    No Known Activations