© 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. 13059
    Prev
    Next
    INDEX
    Explanations

    questions, explanations, or medical terms

    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
    冲
    0.42
    จ
    0.40
    า
    0.40
    线
    0.40
     planned
    0.40
    妞
    0.40
    다
    0.39
    เย
    0.39
     crusade
    0.39
    燁
    0.39
    POSITIVE LOGITS
     pharmacokinetic
    0.53
     analgesic
    0.50
    orcid
    0.49
     glucocortic
    0.48
     elevada
    0.46
     pengendalian
    0.45
    新型コロナ
    0.45
    renerg
    0.45
     hemodynamic
    0.44
     clerg
    0.44
    Activations Density 0.001%

    No Known Activations