© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212167
    Prev
    Next
    INDEX
    Explanations

    academic citations to define

    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_40_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
    occasion
    0.42
     ½
    0.40
    all
    0.39
    VIII
    0.38
     ¼
    0.38
    ½
    0.38
    asal
    0.38
     raya
    0.38
    VII
    0.37
    %,
    0.37
    POSITIVE LOGITS
    עם
    0.43
    த்தே
    0.42
    茈
    0.42
    റ്റ്
    0.41
     neumáticos
    0.41
    苙
    0.40
     Metallurgy
    0.40
     doctrine
    0.39
     Dex
    0.39
    ជាមួយនឹង
    0.39
    Activations Density 0.014%

    No Known Activations