© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112303
    Prev
    Next
    INDEX
    Explanations

    how to check online

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

    The neuron primarily detects the word “check,” especially when used in instructions or queries about verifying something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     And
    -1.75
    ).
    -1.64
     I
    -1.64
    ↵↵↵↵↵↵↵
    -1.63
    ↵↵↵↵
    -1.58
    3
    -1.53
     кроме
    -1.52
     Furthermore
    -1.48
    These
    -1.48
     Moreover
    -1.48
    POSITIVE LOGITS
     how
    2.33
     whether
    1.97
     that
    1.77
     who
    1.73
     through
    1.63
     why
    1.52
     while
    1.49
    kawas
    1.48
     when
    1.42
     informasjon
    1.42
    Activations Density 0.022%

    No Known Activations