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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7860
    Prev
    Next
    INDEX
    Explanations

    actions or states followed by specifics

    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
     Kasus
    -1.07
     sehat
    -1.07
    
    -1.02
     Tidak
    -1.02
     merek
    -1.02
     terbatas
    -1.00
     tomto
    -1.00
    хать
    -0.99
    loài
    -0.99
     cokelat
    -0.98
    POSITIVE LOGITS
     whereby
    1.34
     compare
    1.17
     staffs
    1.15
     Beside
    1.04
     stuffs
    0.97
    Remarks
    0.95
     presume
    0.94
    接近
    0.93
     beside
    0.91
     entitle
    0.90
    Activations Density 0.127%

    No Known Activations