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. 8382
    Prev
    Next
    INDEX
    Explanations

    Hilbert Functions or sourceforge

    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
     Förder
    -0.71
    iteiten
    -0.70
     fall
    -0.69
    🏙
    -0.69
    Bitch
    -0.68
    Political
    -0.68
    ویز
    -0.68
    atic
    -0.66
    tez
    -0.65
     bottlenecks
    -0.65
    POSITIVE LOGITS
    episode
    0.76
     VIV
    0.68
     Intelligen
    0.66
    写真の
    0.66
    诞生
    0.66
     Cé
    0.65
    isSet
    0.64
    Ծանոթ
    0.64
     Literatur
    0.63
    aurav
    0.61
    Activations Density 0.071%

    No Known Activations