© 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. 70367
    Prev
    Next
    INDEX
    Explanations

    employee codes, vulgar past tense, and labels

    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
    Since
    -1.10
     exquisitely
    -1.07
    With
    -1.05
     cleverly
    -1.05
     nestled
    -1.05
    When
    -1.02
    สำหรับ
    -1.01
     heightened
    -1.01
     until
    -0.99
     Since
    -0.99
    POSITIVE LOGITS
     famed
    1.42
     wonderfully
    1.38
     magnificent
    1.32
     lauded
    1.30
     unbelievably
    1.29
     largely
    1.27
     decidedly
    1.26
     wonderful
    1.26
     broader
    1.25
     ridiculously
    1.23
    Activations Density 0.000%

    No Known Activations