© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44791
    Prev
    Next
    INDEX
    Explanations

    AI and machine learning

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

    The main thing this neuron does is detect mentions of artificial intelligence and related technical buzzwords (e.g. AI, machine learning, deep learning, predictive analytics).

    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
     quiero
    -1.66
     grandes
    -1.59
    ፨
    -1.51
    scooter
    -1.48
    痒
    -1.48
    淠
    -1.47
    ⑊
    -1.47
     quero
    -1.45
    蕖
    -1.43
    🛇
    -1.42
    POSITIVE LOGITS
    n
    1.46
    他說
    1.29
     zweimal
    1.24
    ml
    1.23
    g
    1.21
    偶尔
    1.20
    y
    1.19
    <
    1.17
    k
    1.17
     beeind
    1.16
    Activations Density 0.072%

    No Known Activations