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. 103
    Prev
    Next
    INDEX
    Explanations

    ignite, ignites

    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
    執
    -0.80
    文書
    -0.72
    achable
    -0.71
    gq
    -0.68
     eyes
    -0.66
     although
    -0.65
     querying
    -0.64
     illustrating
    -0.64
     aunque
    -0.63
     offset
    -0.63
    POSITIVE LOGITS
    ited
    0.91
     carts
    0.85
     munch
    0.83
     ign
    0.82
    Tengo
    0.81
    bustion
    0.81
     مشاه
    0.79
     diagnosed
    0.78
     Latinoamérica
    0.77
     Ign
    0.75
    Activations Density 0.042%

    No Known Activations