© 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. 213145
    Prev
    Next
    INDEX
    Explanations

    amount and extent

    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
    套
    0.43
     дина
    0.39
    辫
    0.38
    泬
    0.38
     खेळा
    0.38
     সেনাবাহিনীকে
    0.37
     bav
    0.37
    待
    0.37
     Baill
    0.36
    δες
    0.36
    POSITIVE LOGITS
    verified
    0.40
     verified
    0.38
    andelier
    0.38
     autent
    0.38
     uneasy
    0.38
     verifica
    0.38
    poque
    0.37
    कानेर
    0.37
     pembelian
    0.37
     corroborated
    0.37
    Activations Density 0.000%

    No Known Activations