© 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. 26394
    Prev
    Next
    INDEX
    Explanations

    software and technical abbreviations

    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
     if
    -1.47
    ardige
    -1.27
     while
    -1.16
     although
    -1.08
     despite
    -1.07
     to
    -1.03
     since
    -1.03
     penanganan
    -1.00
    اشة
    -1.00
    دانشنامهٔ
    -1.00
    POSITIVE LOGITS
    撂
    1.18
     feiert
    1.11
     verliert
    1.10
     präsentiert
    1.09
    急忙
    1.08
     verbindet
    1.06
    could
    1.05
     bietet
    1.02
     recogida
    1.02
     fordert
    1.01
    Activations Density 0.106%

    No Known Activations