© 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. 67297
    Prev
    Next
    INDEX
    Explanations

    code keywords and sentence beginnings

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

    This neuron detects the “break” keyword used to exit or jump out of a control‐flow block.

    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
     and
    -2.16
     you
    -2.06
     på
    -1.96
    alleros
    -1.94
    老爷子
    -1.91
    顷
    -1.84
    xnn
    -1.84
    lgari
    -1.81
     (‘
    -1.80
    cją
    -1.80
    POSITIVE LOGITS
    5
    2.52
    c
    2.31
    3
    2.28
    m
    2.22
    4
    2.17
    t
    2.16
    2
    2.14
    g
    2.08
    w
    2.08
    s
    2.06
    Activations Density 0.001%

    No Known Activations