© 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. 59468
    Prev
    Next
    INDEX
    Explanations

    deleting files, data, or objects

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

    The neuron is triggered by the word “delete” (in any case or context), i.e. it detects when a deletion command or operation is mentioned.

    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
    s
    -3.63
    ed
    -2.88
    全都
    -2.84
    ↵↵
    -2.75
    "
    -2.73
    se
    -2.58
    翃
    -2.56
    en
    -2.55
    ak
    -2.55
    f
    -2.52
    POSITIVE LOGITS
     parachoque
    3.22
    ↵
    3.03
    ᯾
    2.94
     obstáculos
    2.84
    ╿
    2.58
     brukt
    2.47
     silencioso
    2.45
     forskj
    2.42
     helicópter
    2.42
    ⋟
    2.39
    Activations Density 0.010%

    No Known Activations