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. 102
    Prev
    Next
    INDEX
    Explanations

    sleep and dreams

    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
    ṱ
    -0.88
    過ご
    -0.85
    шит
    -0.76
     khớp
    -0.75
    気味
    -0.73
    種の
    -0.73
     grüne
    -0.72
    غيير
    -0.71
     lingü
    -0.71
    .].
    -0.71
    POSITIVE LOGITS
    itement
    0.94
     napp
    0.82
     Kaisers
    0.78
     armi
    0.78
    全新
    0.77
    POS
    0.77
    𝑶
    0.77
     pandemia
    0.76
    Hyp
    0.75
    麻
    0.75
    Activations Density 0.028%

    No Known Activations