© 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. 59332
    Prev
    Next
    INDEX
    Explanations

    document

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

    The neuron activates on occurrences of the letter sequence “doc” (e.g. in identifiers or keywords referring to documents or document types).

    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
    izzazione
    -1.83
    abinieri
    -1.60
     again
    -1.60
     define
    -1.57
    gencias
    -1.55
    ądz
    -1.55
    鸲
    -1.54
     aDecoder
    -1.53
    柩
    -1.50
    甃
    -1.50
    POSITIVE LOGITS
     there
    2.28
    Even
    1.66
    過去の
    1.66
     time
    1.54
    Both
    1.52
     entendido
    1.49
     навіть
    1.49
    撸
    1.47
    举动
    1.47
    むしろ
    1.45
    Activations Density 0.024%

    No Known Activations