© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118643
    Prev
    Next
    INDEX
    Explanations

    Right SIZE Right HERE

    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
    Hung
    -0.73
    Questa
    -0.69
    reira
    -0.68
    Shark
    -0.65
    کت
    -0.65
    远程
    -0.65
     مكتب
    -0.65
    avocat
    -0.65
    Rounded
    -0.65
     zarar
    -0.64
    POSITIVE LOGITS
     retirement
    1.83
     Retirement
    1.61
     senior
    1.58
     seniors
    1.51
    Retirement
    1.39
     Senior
    1.30
    retirement
    1.29
    senior
    1.22
    Senior
    1.20
     Seniors
    1.18
    Activations Density 0.018%

    No Known Activations