© 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. 60497
    Prev
    Next
    INDEX
    Explanations

    beach and associated places/activities

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

    The main thing this neuron does is detect mentions of the word “beach.”

    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
    ፨
    -2.72
    ور
    -2.52
     nächste
    -2.47
     Menschheit
    -2.31
    IN
    -2.31
    虽说
    -2.27
    .”
    -2.25
    ⤥
    -2.25
     vollständige
    -2.20
    凊
    -2.20
    POSITIVE LOGITS
    臜
    2.80
    y
    2.70
    g
    2.67
    鄠
    2.61
    鳢
    2.56
    祧
    2.53
    鍇
    2.47
     ▸
    2.38
    <bos>
    2.34
     эту
    2.31
    Activations Density 0.004%

    No Known Activations