© 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. 104536
    Prev
    Next
    INDEX
    Explanations

    AppCompat Activity

    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
     to
    -1.36
     on
    -1.30
     its
    -1.26
     if
    -1.13
     екс
    -1.09
     Início
    -1.09
     from
    -1.08
    tikal
    -1.04
    kelijkheid
    -1.02
     in
    -1.01
    POSITIVE LOGITS
    很喜欢
    1.10
     possib
    1.09
     mehrerer
    1.08
     verifiable
    1.07
    verified
    1.06
    从来没有
    1.06
     zubehör
    1.05
     vorigen
    1.04
    ulti
    1.03
     stärker
    1.02
    Activations Density 0.001%

    No Known Activations