© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 112001
    Prev
    Next
    INDEX
    Explanations

    they tend to crawl

    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
     appeared
    0.47
     gleichen
    0.47
    null
    0.45
     nämlich
    0.45
    \_
    0.44
    axis
    0.41
    __)
    0.41
    ischen
    0.41
    circum
    0.41
    même
    0.41
    POSITIVE LOGITS
    ราคา
    0.49
    Цена
    0.46
    Novo
    0.45
    闲
    0.44
    海外
    0.44
    ྒྱ
    0.44
    鍘
    0.44
    📔
    0.44
    櫥
    0.44
    eteor
    0.43
    Activations Density 0.006%

    No Known Activations