© 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. 22-GEMMASCOPE-RES-131K
    7. 12547
    Prev
    Next
    INDEX
    Explanations

    beneficial or useful functions

    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
     lada
    -1.03
    ској
    -1.01
    lious
    -1.00
    seguida
    -0.98
     jee
    -0.97
    ième
    -0.94
     @}
    -0.94
     thun
    -0.94
    wwwww
    -0.93
    ternut
    -0.93
    POSITIVE LOGITS
     beneficial
    1.64
     useful
    1.63
     necessary
    1.46
     sometimes
    1.45
     helpful
    1.41
     benefits
    1.39
     correct
    1.37
     legitimate
    1.37
     иногда
    1.34
     it
    1.25
    Activations Density 0.071%

    No Known Activations