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. 8544
    Prev
    Next
    INDEX
    Explanations

    retrieve by id

    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
     all
    -1.16
    全部
    -0.90
     semua
    -0.88
     همه
    -0.87
    所有
    -0.87
    所有的
    -0.84
     все
    -0.84
     gesagt
    -0.84
     count
    -0.82
     सभी
    -0.82
    POSITIVE LOGITS
     one
    1.63
     findById
    1.29
     by
    1.23
     getById
    1.15
    getOne
    1.13
     findOne
    1.11
    findById
    1.09
     details
    1.09
     find
    1.05
     get
    1.02
    Activations Density 0.004%

    No Known Activations