© 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. 10-GEMMASCOPE-RES-131K
    7. 20699
    Prev
    Next
    INDEX
    Explanations

    phrases including common prepositions

    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
    quirer
    -1.59
     éte
    -1.53
     excès
    -1.49
     occuper
    -1.48
    izie
    -1.48
    carnated
    -1.45
     refroid
    -1.45
     écout
    -1.43
     avancer
    -1.41
     étrang
    -1.38
    POSITIVE LOGITS
     the
    2.05
     my
    1.80
     only
    1.61
     without
    1.55
     which
    1.52
     in
    1.52
     our
    1.48
     most
    1.48
     when
    1.41
     any
    1.39
    Activations Density 0.016%

    No Known Activations