© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109819
    Prev
    Next
    INDEX
    Explanations

    descriptors of quality and category

    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_31_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
    𝒍
    0.48
    Ê
    0.46
     at
    0.44
    𝑰
    0.44
    italization
    0.43
    会儿
    0.43
     initialized
    0.43
    character
    0.43
     करून
    0.43
     redirects
    0.43
    POSITIVE LOGITS
    وة
    0.46
     директор
    0.42
    堅持
    0.42
     независи
    0.41
     ymp
    0.41
    堇
    0.41
     ரசிக
    0.41
    aniyati
    0.41
     gaping
    0.41
    鷗
    0.41
    Activations Density 0.002%

    No Known Activations