© 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. 86165
    Prev
    Next
    INDEX
    Explanations

    cover up

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

    The neuron fires on occurrences of the phrase “cover up” (including its hyphenated form “cover-up”), i.e. instances of concealment.

    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
    (
    -2.22
    并且
    -1.70
    :
    -1.67
    {
    -1.66
    )
    -1.58
    ]
    -1.54
    [
    -1.53
     Erste
    -1.52
    "
    -1.52
    -1.51
    POSITIVE LOGITS
    ↵
    2.44
    u
    2.03
    </strong>
    1.91
    遢
    1.82
     paesaggio
    1.80
     dikutip
    1.78
    rillation
    1.77
    with
    1.75
    她的
    1.70
    寕
    1.69
    Activations Density 0.008%
    No Known Activations