© 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. 40048
    Prev
    Next
    INDEX
    Explanations

    ends up, ends with, ends meet

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

    The neuron specifically detects occurrences of the word “ends.”

    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
     декабря
    -2.61
    鹩
    -2.39
    #,
    -2.25
    ”
    -2.25
    íble
    -2.20
    ,”
    -2.17
    ”？
    -2.17
     and
    -2.17
     января
    -2.16
    ”:
    -2.14
    POSITIVE LOGITS
    There
    2.77
     Could
    2.72
    可能
    2.69
     ends
    2.67
    "
    2.63
    是
    2.58
    If
    2.52
    一定
    2.45
     Ensuring
    2.45
    即使
    2.44
    Activations Density 0.005%

    No Known Activations