© 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. 22-GEMMASCOPE-RES-131K
    7. 104463
    Prev
    Next
    INDEX
    Explanations

    utility package components

    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_22/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
    べた
    -1.15
    řízen
    -1.12
     Væ
    -1.08
     primarily
    -1.06
     and
    -1.06
     probably
    -1.05
     as
    -1.04
    ॰
    -1.04
     it
    -1.02
     mainly
    -1.02
    POSITIVE LOGITS
     jaunes
    1.25
     dô
    1.13
     aéri
    1.13
     merawat
    1.12
    ＊＊＊＊
    1.11
     profond
    1.09
    你的
    1.08
    Sair
    1.08
    Aantal
    1.08
     patate
    1.05
    Activations Density 0.027%

    No Known Activations