© 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. 10-GEMMASCOPE-RES-131K
    7. 66651
    Prev
    Next
    INDEX
    Explanations

    driven [noun/phrase]

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

    The neuron fires on occurrences of the word “driven,” particularly as part of compound adjectives (e.g. data-driven, domain-driven).

    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
    桖
    -3.17
    橚
    -2.52
    ઁ
    -2.50
    躋
    -2.42
     a
    -2.38
    }
    -2.36
    좇
    -2.34
    猻
    -2.31
    来年
    -2.28
     ส์
    -2.28
    POSITIVE LOGITS
    他也
    2.36
    皛
    2.27
    潆
    2.23
     však
    2.22
    м
    2.22
    nyata
    2.19
    ！！”
    2.17
    他不
    2.13
    ”？
    2.11
    )_{
    2.05
    Activations Density 0.006%

    No Known Activations