© 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. 53970
    Prev
    Next
    INDEX
    Explanations

    our you us

    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
     Bucure
    -1.23
     libur
    -1.20
     obstante
    -1.18
     marchand
    -1.11
    ofern
    -1.09
    ździer
    -1.07
    อ่าน
    -1.06
     siècle
    -1.05
     این
    -1.05
    getDatabase
    -1.05
    POSITIVE LOGITS
     our
    2.14
     your
    1.65
     we
    1.31
     Our
    1.19
     you
    1.17
     μας
    1.16
     Shouldn
    1.10
     haremos
    1.08
     שלנו
    1.08
    your
    1.08
    Activations Density 0.150%

    No Known Activations