© 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. 9387
    Prev
    Next
    INDEX
    Explanations

    introductions to mathematical reasoning

    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
     gangen
    -1.29
     hunde
    -1.28
     nedir
    -1.27
    hemd
    -1.18
     Türkçe
    -1.15
     ideen
    -1.14
    banken
    -1.14
    loggen
    -1.13
    ：……
    -1.13
    pantalón
    -1.13
    POSITIVE LOGITS
     but
    1.32
     and
    1.28
    ,
    1.27
    He
    1.15
    or
    1.10
    ~
    1.07
    x
    1.07
    к
    1.06
    よー
    1.05
    ↵
    1.05
    Activations Density 0.003%

    No Known Activations