© 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. 93162
    Prev
    Next
    INDEX
    Explanations

    historical empires and kingdoms

    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
    Each
    -1.55
     Souhaitez
    -1.49
     applicable
    -1.45
    থ্য
    -1.45
     publication
    -1.44
     applications
    -1.43
    ּוֹ
    -1.43
     software
    -1.43
     your
    -1.42
     publications
    -1.42
    POSITIVE LOGITS
     of
    1.90
     ihrer
    1.53
    重置
    1.48
     from
    1.44
     правительства
    1.37
     ihres
    1.35
    обзор
    1.35
    ֩
    1.24
     الطعام
    1.24
     τὴν
    1.24
    Activations Density 0.052%

    No Known Activations