© 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. 19472
    Prev
    Next
    INDEX
    Explanations

    coming from

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

    The neuron is triggered by occurrences of the phrase “coming from,” i.e. references to something’s origin or background.

    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
    人の
    -1.73
     comandante
    -1.70
    —”
    -1.63
    嵛
    -1.55
    𐑂
    -1.52
     aspira
    -1.51
    ча
    -1.51
    Все
    -1.45
    -”
    -1.45
    ”—
    -1.42
    POSITIVE LOGITS
     either
    1.66
    を買う
    1.56
    specifically
    1.53
    盦
    1.53
    気持ちを
    1.51
    了我
    1.51
    primarily
    1.46
    鰯
    1.45
    惴
    1.45
    辚
    1.43
    Activations Density 0.019%

    No Known Activations