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. 8151
    Prev
    Next
    INDEX
    Explanations

    formation and creation

    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
     restored
    -0.90
     performs
    -0.89
    Designs
    -0.85
    做得
    -0.84
    又要
    -0.83
    还想
    -0.79
    使って
    -0.79
     appoints
    -0.79
     solutions
    -0.79
     arrangements
    -0.79
    POSITIVE LOGITS
     process
    1.27
     and
    1.26
    過程
    0.97
     процесс
    0.93
     Entste
    0.93
     Process
    0.89
     fabricar
    0.89
    asun
    0.88
    process
    0.88
    itext
    0.88
    Activations Density 0.079%

    No Known Activations