© 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. 84152
    Prev
    Next
    INDEX
    Explanations

    verbs introducing statements

    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
     trozos
    -1.13
     cremallera
    -1.03
     bloques
    -1.02
    告诉我
    -0.99
     comportements
    -0.98
    脸上
    -0.97
     וּ
    -0.96
    樫
    -0.96
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.94
     chercheurs
    -0.94
    POSITIVE LOGITS
     to
    1.82
     my
    1.52
     that
    1.29
     this
    1.21
     in
    1.13
     myself
    1.06
     because
    1.04
    rceil
    1.04
     them
    1.03
     If
    1.01
    Activations Density 0.038%

    No Known Activations