© 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. 81668
    Prev
    Next
    INDEX
    Explanations

    Grant, sexuality, or punctuation

    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
     الع
    0.45
     zoals
    0.42
     વ
    0.41
    шість
    0.41
    ή
    0.41
     της
    0.40
     الح
    0.40
     pole
    0.40
     الت
    0.39
    در
    0.39
    POSITIVE LOGITS
     власти
    0.44
     when
    0.42
     किन्न
    0.40
     när
    0.39
    ña
    0.39
    চনায়
    0.39
     Особенно
    0.39
     inade
    0.39
     экспеди
    0.38
    걱
    0.38
    Activations Density 0.009%

    No Known Activations