© 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. 10-GEMMASCOPE-RES-131K
    7. 45278
    Prev
    Next
    INDEX
    Explanations

    versus, vs, comparing

    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_10/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
     CONSTITUTION
    -1.34
    ανα
    -1.31
    ichtlich
    -1.31
     again
    -1.30
    ]}\
    -1.27
     EMER
    -1.26
    ämie
    -1.26
    ailangan
    -1.21
    ствовать
    -1.20
     LANDSCAPE
    -1.20
    POSITIVE LOGITS
     nawet
    1.39
     versus
    1.29
    動か
    1.17
    比べて
    1.16
     logrado
    1.16
     same
    1.16
    並んで
    1.14
     vs
    1.13
    lewati
    1.13
     unor
    1.12
    Activations Density 0.199%

    No Known Activations