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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49262
    Prev
    Next
    INDEX
    Explanations

    all

    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
     derselben
    -1.27
     genauer
    -1.22
     ihrem
    -1.16
     their
    -1.13
     lustige
    -1.12
     zumindest
    -1.11
     anzi
    -1.11
     first
    -1.08
    AppRoutingModule
    -1.07
     jenes
    -1.06
    POSITIVE LOGITS
     all
    5.25
    这些
    3.55
    這些
    3.23
     these
    3.05
    这一切
    2.88
     semua
    2.75
     όλα
    2.69
     toate
    2.59
     همه
    2.55
     semuanya
    2.52
    Activations Density 0.073%

    No Known Activations