© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75432
    Prev
    Next
    INDEX
    Explanations

    measuring abstract quantities

    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_34/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
     CERTAIN
    -1.27
     eerste
    -1.27
     szép
    -1.25
     Джа
    -1.17
     majeurs
    -1.14
     causation
    -1.12
     brillantes
    -1.12
     mía
    -1.11
    InstrumentedTest
    -1.10
     peruan
    -1.09
    POSITIVE LOGITS
     type
    3.05
     amount
    2.56
     size
    2.45
     length
    2.30
     level
    2.28
     types
    2.25
     degree
    2.23
     nature
    2.03
     extent
    2.02
     kind
    1.98
    Activations Density 0.117%

    No Known Activations