© 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. 79898
    Prev
    Next
    INDEX
    Explanations

    obviously clear

    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
     Maybe
    -1.27
     possibly
    -1.25
     often
    -1.24
     believes
    -1.22
     may
    -1.21
     seemed
    -1.18
     oftentimes
    -1.18
     might
    -1.16
     it
    -1.16
     two
    -1.16
    POSITIVE LOGITS
    obviously
    3.16
     obviously
    2.78
     évidemment
    2.50
     ovviamente
    2.47
     oczywiście
    2.39
    當然
    2.28
    Obviously
    2.23
     obviamente
    2.17
     конечно
    2.05
     obvious
    2.03
    Activations Density 0.119%

    No Known Activations