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. 195
    Prev
    Next
    INDEX
    Explanations

    nematode

    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
    irdre
    -0.81
    Loan
    -0.77
    kembangkan
    -0.73
    ल्स
    -0.73
     Compre
    -0.70
    uchos
    -0.69
    SPELL
    -0.69
     petugas
    -0.69
    ltä
    -0.69
    Jahres
    -0.69
    POSITIVE LOGITS
     nematodes
    2.11
     nematode
    2.03
     Nem
    1.84
     nemat
    1.69
     Nema
    1.38
    Nem
    1.35
     ne
    1.17
    NEM
    1.16
     nema
    1.14
     NEM
    1.13
    Activations Density 0.048%

    No Known Activations