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. 8212
    Prev
    Next
    INDEX
    Explanations

    data stream or request

    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
    روسية
    -0.73
    自
    -0.73
    🫁
    -0.72
     Fah
    -0.71
    enseits
    -0.69
     என்ற
    -0.69
    selbst
    -0.69
    ciado
    -0.68
    時刻
    -0.67
    Decoding
    -0.66
    POSITIVE LOGITS
     dat
    1.58
     Dat
    1.37
     Data
    1.36
     virtual
    1.32
     room
    1.30
    Dat
    1.28
    DAT
    1.22
     data
    1.21
     rooms
    1.17
     DAT
    1.17
    Activations Density 0.166%

    No Known Activations