© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15271
    Prev
    Next
    INDEX
    Explanations

    can see shown

    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
    autorelease
    -1.30
    Ưu
    -1.24
     their
    -1.23
     this
    -1.22
    bản
    -1.16
    tôi
    -1.14
     &___
    -1.13
     fön
    -1.13
    tarta
    -1.10
     béisbol
    -1.09
    POSITIVE LOGITS
     eingeladen
    1.08
     vielmehr
    1.03
     contribuer
    1.02
    ัตร
    1.01
     trol
    1.00
     дешевле
    0.99
     aquella
    0.99
    C
    0.98
    Affiliations
    0.98
     culturale
    0.94
    Activations Density 0.039%

    No Known Activations