© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3271
    Prev
    Next
    INDEX
    Explanations

    The Trevor Project or LGBTQ youth support

    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
    Negative Logits
    わり
    0.78
    自己
    0.76
    シンプルな
    0.76
     úpl
    0.75
    ตัวเอง
    0.74
    IV
    0.74
     খোলা
    0.74
    "^
    0.72
    ărat
    0.71
     मक्
    0.71
    POSITIVE LOGITS
     mash
    0.75
    ாலும்
    0.73
     graduation
    0.73
    peut
    0.73
     cork
    0.72
    냈
    0.71
    itura
    0.69
     Dương
    0.69
    unately
    0.69
     pud
    0.69
    Activations Density 0.032%

    No Known Activations