© 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. 51556
    Prev
    Next
    INDEX
    Explanations

    likelihood of benefit

    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
     современной
    0.46
    こんにちは
    0.46
     말했다
    0.46
    开发
    0.45
    尽管
    0.44
    甚至
    0.43
    甚至是
    0.43
    ๊
    0.42
    esehatan
    0.42
     रखरखाव
    0.41
    POSITIVE LOGITS
    which
    0.50
     which
    0.50
    that
    0.49
    for
    0.48
     efektif
    0.46
     achie
    0.46
    approval
    0.45
     being
    0.45
    ohm
    0.44
     osią
    0.44
    Activations Density 0.012%

    No Known Activations