© 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. 35147
    Prev
    Next
    INDEX
    Explanations

    physical and abstract entities

    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
    को
    -0.89
     after
    -0.89
     being
    -0.87
     or
    -0.86
     gloire
    -0.86
    自分が
    -0.85
     embalaje
    -0.85
     having
    -0.85
    颐
    -0.84
    рованная
    -0.83
    POSITIVE LOGITS
     into
    1.55
    使其
    1.24
     khiến
    1.20
     결과
    1.09
    resulting
    1.04
    ergies
    0.98
    UNCIL
    0.93
     NavController
    0.93
     resulted
    0.93
     باعث
    0.93
    Activations Density 0.138%

    No Known Activations