© 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. 22-GEMMASCOPE-RES-131K
    7. 129714
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
     começar
    -1.06
    ulemon
    -1.06
     ὁ
    -1.06
    𝐽
    -1.05
    istani
    -1.05
    ស
    -1.04
     яйцо
    -1.03
    лни
    -1.01
    ក
    -0.99
     querían
    -0.99
    POSITIVE LOGITS
    1.10
     ネタバレ
    1.06
    InkWell
    1.02
    owicz
    1.00
    ਖ਼
    1.00
     הייתה
    0.98
     arbeits
    0.98
     будущего
    0.97
     noodzake
    0.97
     chức
    0.96
    Activations Density 0.001%
    No Known Activations