© 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. 64816
    Prev
    Next
    INDEX
    Explanations

    sequence/temporal progression

    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
    
    -1.18
    gered
    -1.13
    ΅
    -1.11
     herunterladen
    -1.10
    他已经
    -1.05
     verhind
    -1.05
     INTERFACE
    -1.05
    ：　
    -1.04
    🙁
    -1.04
     ALUMIN
    -1.03
    POSITIVE LOGITS
     later
    2.02
     began
    1.63
    その後
    1.62
     thereafter
    1.62
     until
    1.61
     then
    1.49
     Kemudian
    1.47
     Later
    1.38
     THEN
    1.32
     بعد
    1.29
    Activations Density 0.050%

    No Known Activations