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. 8225
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
     get
    -1.03
     है
    -0.91
     but
    -0.90
    ⍳
    -0.87
    AndGet
    -0.87
     to
    -0.85
     first
    -0.82
     gets
    -0.82
     specified
    -0.82
     hingga
    -0.79
    POSITIVE LOGITS
    :“……”
    1.08
    ându
    0.98
     hacerle
    0.95
     setCurrent
    0.94
    clear
    0.94
     prévoit
    0.94
     garantit
    0.93
    %).
    0.92
     fără
    0.90
     patrie
    0.90
    Activations Density 0.022%

    No Known Activations