© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 41005
    Prev
    Next
    INDEX
    Explanations

    Parameter-Efficient Fine-Tuning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Darby
    0.41
    卯
    0.39
     Дар
    0.39
    အစိတ်အပိုင်း
    0.37
     dar
    0.37
     感
    0.37
    ມື
    0.36
    DAR
    0.36
     salam
    0.35
    Dar
    0.35
    POSITIVE LOGITS
     jr
    0.45
    akon
    0.41
     सीताराम
    0.39
     Jr
    0.39
     Ears
    0.37
     Ir
    0.36
     Junior
    0.36
    横
    0.36
    doctrine
    0.36
    личи
    0.36
    Activations Density 0.007%

    No Known Activations