© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69559
    Prev
    Next
    INDEX
    Explanations

    determiners and list introductions

    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
     seemed
    -1.68
     epitom
    -1.52
     there
    -1.52
     refused
    -1.51
     drastically
    -1.48
     urged
    -1.44
     undeniably
    -1.40
     allows
    -1.38
     several
    -1.38
     people
    -1.38
    POSITIVE LOGITS
    盌
    1.59
    睃
    1.56
     mesmerizing
    1.50
     :"
    1.47
    觚
    1.45
    -\\
    1.41
     Finally
    1.41
     partager
    1.40
     cardin
    1.40
     dilapidated
    1.38
    Activations Density 0.289%

    No Known Activations