© 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. 36099
    Prev
    Next
    INDEX
    Explanations

    superlative descriptions

    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
     ponieważ
    -1.20
    了许多
    -1.13
    oluble
    -1.13
     dlatego
    -1.08
    というか
    -1.07
     gdyż
    -1.05
     এবং
    -1.04
    ضات
    -1.03
    3
    -0.98
    8
    -0.98
    POSITIVE LOGITS
    oblastoma
    1.00
     ever
    1.00
     most
    0.98
    ZIONE
    0.97
     arguably
    0.96
    iems
    0.94
     there
    0.93
    !=-
    0.92
    Ṛ
    0.91
    arXiv
    0.90
    Activations Density 0.053%

    No Known Activations