© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59565
    Prev
    Next
    INDEX
    Explanations

    should be

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

    The neuron fires on the modal verb “should,” flagging instances of “should” in the text.

    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
    ⎔
    -2.66
    ᯾
    -2.48
    ఽ
    -2.39
    ⬈
    -2.34
    沨
    -2.34
    씰
    -2.31
    
    -2.31
    苤
    -2.28
    龉
    -2.28
    ators
    -2.22
    POSITIVE LOGITS
    '
    3.41
    (
    2.61
    t
    2.50
    j
    2.17
    In
    2.17
    </td>
    2.16
    At
    2.08
    On
    2.03
    ?
    1.98
     =
    1.96
    Activations Density 0.026%

    No Known Activations