© 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. 84304
    Prev
    Next
    INDEX
    Explanations

    completion or cessation

    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
     không
    -0.96
     senza
    -0.95
    PETS
    -0.88
     without
    -0.86
    まずは
    -0.85
     bilan
    -0.84
     franca
    -0.84
    ung
    -0.84
    abb
    -0.82
    not
    -0.81
    POSITIVE LOGITS
     until
    1.63
     till
    1.41
     jusqu
    1.22
    until
    1.20
     UNTIL
    1.13
     despite
    1.13
    จน
    1.09
     Öffnungszeiten
    1.09
     nor
    1.07
     yesterday
    1.05
    Activations Density 0.060%

    No Known Activations