© 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. 44387
    Prev
    Next
    INDEX
    Explanations

    contextual variation in language

    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
     of
    -2.06
     about
    -1.31
     berücksichtigt
    -1.30
     sekaligus
    -1.29
     الذي
    -1.24
     lequel
    -1.20
     bedeckt
    -1.18
    і
    -1.15
     eingerichtet
    -1.14
     bilhões
    -1.14
    POSITIVE LOGITS
     there
    1.84
    stantial
    1.35
    kolwiek
    1.30
     would
    1.26
    嫱
    1.25
    epam
    1.24
     it
    1.23
    SPONSORED
    1.21
     bonté
    1.20
     dapatkan
    1.19
    Activations Density 0.020%

    No Known Activations