© 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. 44147
    Prev
    Next
    INDEX
    Explanations

    doing something effectively

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

    The neuron activates strongly on the adverb “effectively.”

    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
    ↵↵
    -2.41
    zenie
    -2.27
     stark
    -2.16
    ೣ
    -2.08
     definitive
    -1.98
     thier
    -1.95
    钺
    -1.95
     opulent
    -1.94
     elevating
    -1.92
    lässlich
    -1.91
    POSITIVE LOGITS
     Hinblick
    2.67
    ”،
    2.50
    That
    2.39
     δεν
    2.34
     онъ
    2.20
    って思
    2.20
    When
    2.13
    If
    2.11
     magnétique
    2.11
     кілька
    2.09
    Activations Density 0.005%

    No Known Activations