© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104501
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols

    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
     ſever
    -1.20
    iiii
    -1.17
     két
    -1.16
    outputStream
    -1.16
     достижения
    -1.14
     ajouter
    -1.13
     добав
    -1.10
     COMMUNITY
    -1.09
     tém
    -1.06
    䜣
    -1.06
    POSITIVE LOGITS
     now
    1.44
    漁港
    1.36
    岘
    1.30
     enigma
    1.25
    ここでは
    1.23
     unrelenting
    1.17
     striving
    1.17
     ဝ
    1.16
    民宿
    1.16
     plethora
    1.15
    Activations Density 0.002%

    No Known Activations