© 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. 72423
    Prev
    Next
    INDEX
    Explanations

    free birth control, custom layouts, self-assembly

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

    The neuron detects chunks of Chinese text.

    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
    genodigd
    -2.97
     zeven
    -2.91
     
    -2.89
    祧
    -2.61
     beider
    -2.55
    那我
    -2.53
     wob
    -2.53
    氿
    -2.48
     spezi
    -2.44
    ated
    -2.41
    POSITIVE LOGITS
    しました
    3.13
     剤
    2.92
    eadilan
    2.86
     });
    2.83
    琑
    2.70
    鶘
    2.66
    ные
    2.63
    鲼
    2.63
     puts
    2.58
    チュラル
    2.58
    Activations Density 0.000%

    No Known Activations