© 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. 70410
    Prev
    Next
    INDEX
    Explanations

    ingredients and their modifiers

    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
    ☫
    -1.33
     dianteiro
    -1.27
     traseira
    -1.20
    ерез
    -1.15
     sucre
    -1.14
    kapnya
    -1.13
    itisation
    -1.13
    swire
    -1.13
    職人
    -1.12
    oys
    -1.11
    POSITIVE LOGITS
     or
    1.23
     càng
    1.06
     menawarkan
    1.03
     preferably
    1.02
     good
    1.00
     miał
    1.00
     beobachtet
    0.99
     while
    0.99
     nuevamente
    0.98
    škas
    0.98
    Activations Density 0.038%

    No Known Activations