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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59837
    Prev
    Next
    INDEX
    Explanations

    plan skip, guide, container, pricing

    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_10/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
     jezt
    -2.75
    ࿙
    -2.73
     unſ
    -2.73
    蜮
    -2.70
     Він
    -2.55
    ྅
    -2.52
     possono
    -2.45
    ↵
    -2.45
    鬭
    -2.44
     ſch
    -2.41
    POSITIVE LOGITS
    u
    4.03
    la
    3.80
    an
    3.48
    You
    3.41
    as
    3.11
     he
    3.09
    x
    3.08
    j
    2.97
     =
    2.97
    p
    2.95
    Activations Density 0.024%

    No Known Activations