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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    align to center

    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_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
     Folding
    0.82
     folding
    0.81
     ინტერ
    0.79
     interlayer
    0.77
    ွက်
    0.76
     ピンク
    0.75
    咖
    0.73
     між
    0.73
     Zwischen
    0.73
    綘
    0.73
    POSITIVE LOGITS
     center
    1.50
    center
    1.48
    Center
    1.39
     centers
    1.30
    centers
    1.26
     Center
    1.25
    CENTER
    1.25
     centro
    1.23
     центру
    1.20
     centre
    1.20
    Activations Density 0.083%

    No Known Activations