© 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. 22463
    Prev
    Next
    INDEX
    Explanations

    wipe out

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

    The neuron is triggered by occurrences of the verb “wipe” (in any inflected form, e.g. wipes, wiped) often conveying erasure or removal.

    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
    _
    -3.92
    >
    -3.89
    B
    -3.64
    A
    -3.64
    (
    -3.64
     \
    -3.59
    \
    -3.48
    ”
    -3.27
    T
    -3.03
    Y
    -2.94
    POSITIVE LOGITS
    karena
    3.02
    鯪
    2.97
    鱨
    2.95
     ſta
    2.86
    纐
    2.69
    Kenapa
    2.69
    喁
    2.67
    
    2.61
    Semua
    2.59
    絰
    2.59
    Activations Density 0.002%

    No Known Activations