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. 7876
    Prev
    Next
    INDEX
    Explanations

    prevailing conditions

    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
    ritzau
    -0.81
    出
    -0.80
    rifts
    -0.79
    located
    -0.79
    included
    -0.78
    grub
    -0.78
    watching
    -0.77
     í
    -0.76
     startDate
    -0.76
     sabemos
    -0.75
    POSITIVE LOGITS
     prevailing
    4.69
     prevail
    3.77
     prevailed
    3.63
     prevails
    3.59
     prevalent
    3.20
     preval
    2.38
     preva
    2.36
     existing
    2.30
     reigning
    2.27
     herrs
    2.19
    Activations Density 0.088%

    No Known Activations