© 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. 44732
    Prev
    Next
    INDEX
    Explanations

    visibility in code

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

    The neuron primarily responds to the attribute name “Visibility.”

    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
     ۱۰
    -2.39
    UCIÓN
    -2.36
     ۱۱
    -2.36
    x
    -2.36
    鱻
    -2.28
     видит
    -2.25
    ffiche
    -2.13
     –
    -2.13
     ۲۵
    -2.11
    ȧ
    -2.11
    POSITIVE LOGITS
    ’
    2.20
     l
    2.16
     сожа
    2.14
     "";
    2.09
     аккура
    2.09
    </strong>
    2.02
     нарушение
    1.98
    ''
    1.93
     зелё
    1.91
    CGRectMake
    1.90
    Activations Density 0.000%

    No Known Activations