© 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. 98232
    Prev
    Next
    INDEX
    Explanations

    case study examples

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

    The neuron fires on mentions of “case”–style examples (e.g. “case study,” “case reports,” “case presentation”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    专注
    -1.14
    图源
    -1.14
     nedan
    -0.99
    套装
    -0.96
     básicos
    -0.94
    了下
    -0.92
    esters
    -0.92
     portavoz
    -0.92
     instructions
    -0.91
     prerequisites
    -0.90
    POSITIVE LOGITS
     of
    2.23
     case
    1.67
     cases
    1.58
     examples
    1.58
    事例
    1.36
     example
    1.31
     from
    1.19
    ケース
    1.15
     конкре
    1.13
    ubernur
    1.10
    Activations Density 0.072%

    No Known Activations