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. 8498
    Prev
    Next
    INDEX
    Explanations

    just like or want

    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
    ก็
    -1.21
    gehen
    -1.18
     realmente
    -1.17
    ticularly
    -1.16
     ats
    -1.13
     gustar
    -1.13
     ſou
    -1.13
    และ
    -1.12
     kompet
    -1.11
    geladen
    -1.11
    POSITIVE LOGITS
     only
    2.09
     by
    1.80
    Only
    1.60
     лишь
    1.57
     for
    1.55
     merely
    1.55
     few
    1.51
     before
    1.45
     Only
    1.45
     ONLY
    1.39
    Activations Density 0.028%

    No Known Activations