© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19575
    Prev
    Next
    INDEX
    Explanations

    history, genetic, text, objects

    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
    助
    0.43
    ivating
    0.42
     transformers
    0.42
     trident
    0.41
    ﺶ
    0.41
     bolder
    0.41
    ウエスト
    0.41
     waist
    0.40
     pouch
    0.40
     पनि
    0.40
    POSITIVE LOGITS
     memoria
    0.46
     dilaksanakan
    0.46
     Ș
    0.45
     கருத்து
    0.44
    ograma
    0.44
     удалить
    0.44
     Кри
    0.43
     Colegio
    0.43
     વિદ્યાર્થી
    0.43
    Tarefa
    0.42
    Activations Density 0.001%

    No Known Activations