© 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. 92842
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connector words

    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
     milligrams
    0.50
     freestanding
    0.46
     microsomal
    0.42
     laptops
    0.41
    :<
    0.39
     coarsely
    0.39
     triglyceride
    0.39
     cassettes
    0.39
     destinations
    0.39
    时候
    0.38
    POSITIVE LOGITS
     akan
    0.50
    佾
    0.50
     zde
    0.48
     попыта
    0.48
     Polit
    0.47
    الح
    0.46
     aggior
    0.46
     polít
    0.46
     вирі
    0.46
     dari
    0.45
    Activations Density 0.013%

    No Known Activations