© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 194552
    Prev
    Next
    INDEX
    Explanations

    accuracy or parts

    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_40_width_262k_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
     পাদ
    0.37
     linking
    0.36
    펀
    0.36
     gross
    0.36
     visu
    0.35
     MEG
    0.35
     drawer
    0.34
     Main
    0.34
    روز
    0.34
     coarser
    0.34
    POSITIVE LOGITS
    थम
    0.42
    強く
    0.42
    sei
    0.40
    랜드
    0.40
     Epidemi
    0.40
    ït
    0.39
     Nella
    0.38
    铁
    0.38
     culmin
    0.37
     বিকেলে
    0.37
    Activations Density 0.000%

    No Known Activations