© 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. 22-GEMMASCOPE-RES-131K
    7. 39121
    Prev
    Next
    INDEX
    Explanations

    general concepts and entities

    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
    -1.50
     not
    -1.50
     one
    -1.45
     mainly
    -1.34
     as
    -1.34
     &
    -1.34
     mostly
    -1.28
     first
    -1.27
     at
    -1.26
     different
    -1.25
    POSITIVE LOGITS
     médicaments
    1.43
    
    1.36
     maniere
    1.35
     imprimer
    1.33
     véritables
    1.31
     vingt
    1.30
     quinze
    1.30
     utilisez
    1.29
     traitements
    1.29
     ingrédients
    1.28
    Activations Density 0.611%

    No Known Activations