© 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-16K
    7. 4046
    Prev
    Next
    INDEX
    Explanations

    codes and conventions

    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_16k_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
    璁
    0.48
     劉
    0.47
     היה
    0.44
     অনুরোধ
    0.43
     recounted
    0.43
    データを
    0.43
    цом
    0.43
     የመጀመሪያ
    0.43
     contaba
    0.42
     கவு
    0.41
    POSITIVE LOGITS
     nebo
    0.55
     ή
    0.54
    或
    0.54
     hoặc
    0.53
     eller
    0.52
     theater
    0.52
     arteries
    0.52
     alebo
    0.52
     symptom
    0.50
    或者
    0.50
    Activations Density 0.001%

    No Known Activations