© 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. 10-GEMMASCOPE-RES-131K
    7. 110603
    Prev
    Next
    INDEX
    Explanations

    starting a business

    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_10/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
     prendra
    -1.58
    桫
    -1.47
     restera
    -1.45
    詎
    -1.42
     RESTAURANT
    -1.38
    grandchildren
    -1.38
     ſhall
    -1.36
     venerdì
    -1.35
     チ
    -1.34
     devra
    -1.34
    POSITIVE LOGITS
    ?”
    2.00
    !”
    1.85
     ‘
    1.80
     a
    1.66
     in
    1.59
    .”
    1.50
    ,”
    1.47
     Erkrank
    1.44
    ”:
    1.44
    hawatir
    1.39
    Activations Density 0.043%

    No Known Activations