© 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. 39315
    Prev
    Next
    INDEX
    Explanations

    ```class definitions and declarations```

    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
     still
    -1.08
    Still
    -1.06
    still
    -1.05
    さらに
    -1.04
    由于
    -1.01
     now
    -1.01
    слав
    -0.99
    一般
    -0.97
    安全
    -0.96
    此时
    -0.96
    POSITIVE LOGITS
     moest
    1.02
    绺
    1.02
    Kli
    0.98
    炁
    0.97
     jambe
    0.97
    だけは
    0.96
     mocht
    0.96
    Liet
    0.96
    いかが
    0.95
    commissioned
    0.95
    Activations Density 0.002%

    No Known Activations