© 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. 34-GEMMASCOPE-RES-131K
    7. 65059
    Prev
    Next
    INDEX
    Explanations

    for the sake of

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

    The neuron detects the idiomatic phrase “for the sake of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Singer
    -0.86
    Sn
    -0.79
    鏡
    -0.75
    Ἔ
    -0.71
    UOUS
    -0.68
    Sad
    -0.67
    endront
    -0.66
     soirée
    -0.66
     DeL
    -0.66
    ungeons
    -0.65
    POSITIVE LOGITS
     sake
    3.41
     ради
    3.41
    ради
    1.95
     Ради
    1.91
     wegen
    1.73
     kvůli
    1.48
     зара
    1.41
     causa
    1.24
    是为了
    1.22
     เพื่อ
    1.14
    Activations Density 0.028%

    No Known Activations