Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8352
    Prev
    Next
    INDEX
    Explanations

    a and an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     одном
    -1.04
    someone
    -1.02
    何か
    -1.00
    postolic
    -0.99
    numb
    -0.91
     reçoit
    -0.90
     qualcosa
    -0.90
     iemand
    -0.90
    ceptable
    -0.89
     indicando
    -0.89
    POSITIVE LOGITS
     a
    4.84
     an
    3.28
     একটি
    1.72
    是一个
    1.66
    一个
    1.63
     một
    1.44
    是个
    1.44
     eine
    1.41
    了一個
    1.40
     एक
    1.38
    Activations Density 0.267%

    No Known Activations