© 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. 10-GEMMASCOPE-RES-131K
    7. 111247
    Prev
    Next
    INDEX
    Explanations

    identifying class names

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "ClassName" in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    th
    -2.47
    
    -2.42
     \
    -2.42
    ,
    -2.36
    OUTUBE
    -2.33
    это
    -2.27
    )
    -2.25
     说
    -2.17
     okazji
    -2.17
    yeah
    -2.16
    POSITIVE LOGITS
    
    2.63
    section
    2.39
    餿
    2.38
    )'
    2.30
    鴬
    2.19
    ⁧
    2.17
    豋
    2.17
    깐
    2.17
    ↵
    2.14
    𝔗
    2.13
    Activations Density 0.002%

    No Known Activations