© 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. 22-GEMMASCOPE-RES-131K
    7. 15795
    Prev
    Next
    INDEX
    Explanations

    many followed by noun

    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
     two
    -1.24
     most
    -1.20
     even
    -1.13
     particular
    -1.02
     main
    -1.02
     mainly
    -1.01
    最
    -0.99
     almost
    -0.97
     nearly
    -0.96
     with
    -0.95
    POSITIVE LOGITS
     diversas
    1.09
    excellent
    1.06
     여러
    1.03
     myriad
    1.02
     berbagai
    1.02
    many
    0.99
     available
    0.98
     variety
    0.98
     MANY
    0.98
     mnoho
    0.98
    Activations Density 0.064%

    No Known Activations