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. 82
    Prev
    Next
    INDEX
    Explanations

    Howtextcodesquestions

    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
     ahol
    -0.98
     músculo
    -0.85
     FetchType
    -0.82
     Miß
    -0.82
    片刻
    -0.82
    特别
    -0.82
    кура
    -0.80
    osaurus
    -0.79
    üße
    -0.79
    indd
    -0.78
    POSITIVE LOGITS
     isset
    0.99
     Galería
    0.89
    就没
    0.84
    agreb
    0.84
    脸上
    0.81
    コーデ
    0.80
    虽说
    0.78
     Proverbs
    0.77
    漀
    0.77
     sulit
    0.73
    Activations Density 0.000%

    No Known Activations