© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69687
    Prev
    Next
    INDEX
    Explanations

    shake off

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

    This neuron responds to the particle “off” in phrasal verbs (e.g. shake off, shrug off, brush off) that indicate dismissing or discarding.

    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
     maquinaria
    -1.66
    齣
    -1.65
    だったが
    -1.63
     tetapi
    -1.63
    躥
    -1.62
    昕
    -1.58
    靺
    -1.56
     ребенок
    -1.54
    限り
    -1.54
     WILDLIFE
    -1.52
    POSITIVE LOGITS
     некоторы
    1.70
    autoreleasepool
    1.57
    嫱
    1.53
     někter
    1.49
    gleichen
    1.48
    řízení
    1.44
     bazı
    1.43
    𖣘
    1.43
     ofreci
    1.42
    𝐎
    1.42
    Activations Density 0.009%

    No Known Activations