© 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. 74887
    Prev
    Next
    INDEX
    Explanations

    logical unit, path, and database

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

    The neuron strongly lights up on technical terms that denote abstraction layers or resource types—especially “logical,” “physical,” or “virtual” qualifiers (e.g. logical unit, logical volume, physical device).

    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
    缡
    -1.64
    螣
    -1.50
     stdClass
    -1.45
     so
    -1.44
    剮
    -1.41
     conexión
    -1.36
    BIÉN
    -1.30
    ти
    -1.29
     niektor
    -1.29
    chnung
    -1.28
    POSITIVE LOGITS
     anspruchs
    1.63
     discernible
    1.51
     zusätzlichen
    1.45
    剷
    1.44
     there
    1.41
     crafty
    1.41
    也會
    1.38
    这也是
    1.37
    iermark
    1.37
     geprü
    1.36
    Activations Density 0.048%

    No Known Activations