© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98516
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
     both
    -1.31
     every
    -1.28
     our
    -1.20
     new
    -1.17
     which
    -1.14
     should
    -1.13
     pengobatan
    -1.13
     any
    -1.13
     changes
    -1.12
     all
    -1.11
    POSITIVE LOGITS
     mesmerizing
    1.31
    again
    1.27
    referred
    1.24
     ridiculously
    1.22
     wondrous
    1.21
     secluded
    1.20
     breathtaking
    1.19
     splendid
    1.18
     Again
    1.16
     magnificent
    1.16
    Activations Density 0.001%

    No Known Activations