© 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. 116471
    Prev
    Next
    INDEX
    Explanations

    protecting against

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

    The neuron activates on occurrences of the root “protect” (e.g. protect, protecting, protection).

    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
    鼙
    -1.06
     préférable
    -0.93
    ək
    -0.91
    ajuku
    -0.90
    𐌸
    -0.89
     ailment
    -0.88
    が悪い
    -0.88
     bruin
    -0.88
     servire
    -0.88
     récomp
    -0.87
    POSITIVE LOGITS
     against
    2.45
     from
    2.14
     vulnerable
    1.95
    Against
    1.67
     Against
    1.48
     khỏi
    1.39
    against
    1.38
     interests
    1.33
     integrity
    1.27
     fragile
    1.19
    Activations Density 0.029%

    No Known Activations