© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130675
    Prev
    Next
    INDEX
    Explanations

    hell, I

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

    The neuron detects emphatic interjections “hell” (and its euphemistic variant “heck”) used as standalone intensifiers.

    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
     berbasis
    -1.43
    interopRequire
    -1.42
    ”)
    -1.41
     berdasarkan
    -1.41
    以免
    -1.38
     良品
    -1.38
     thoſe
    -1.35
    érons
    -1.35
    šla
    -1.34
    ｓ
    -1.34
    POSITIVE LOGITS
     if
    1.58
     abbildung
    1.45
     already
    1.45
     even
    1.42
     είναι
    1.41
     angefü
    1.41
     großartige
    1.40
    鍆
    1.38
    そのため
    1.37
    ll
    1.35
    Activations Density 0.004%

    No Known Activations