© 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. 71288
    Prev
    Next
    INDEX
    Explanations

    replacing or covering content

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

    The neuron strongly activates on occurrences of the word “overriding.”

    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
    1
    -3.11
    "
    -3.05
    2
    -2.94
    an
    -2.84
    -
    -2.78
    is
    -2.77
    Not
    -2.67
    6
    -2.64
    Since
    -2.64
    Now
    -2.61
    POSITIVE LOGITS
    剮
    3.25
    🧌
    3.00
    姽
    2.94
    ⬈
    2.92
    夤
    2.84
    
    2.81
     inteligen
    2.78
    特斯拉
    2.75
    jaqueta
    2.73
    ⩴
    2.72
    Activations Density 0.001%

    No Known Activations