© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12168
    Prev
    Next
    INDEX
    Explanations

    one, trans, noscript, Synthesis, #, by

    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_22/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
    我們
    -1.04
    皆さん
    -1.01
     everybody
    -1.01
     seldom
    -0.97
    职位
    -0.96
    Because
    -0.92
    我們的
    -0.92
    መ
    -0.90
     наших
    -0.90
     remet
    -0.88
    POSITIVE LOGITS
    see
    1.27
    柠
    1.27
    different
    1.11
    quiz
    1.06
    ionado
    1.05
    даль
    1.02
    ToListAsync
    1.00
    though
    0.98
     olika
    0.97
     quindi
    0.95
    Activations Density 0.001%

    No Known Activations