© 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. 66223
    Prev
    Next
    INDEX
    Explanations

    html structure and layout

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

    The neuron is triggered by CSS display/visibility keywords (e.g. “hidden” or “block”).

    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
    Ꮗ
    -1.80
    สำหรับ
    -1.57
     också
    -1.55
     için
    -1.54
     llor
    -1.52
     gustaMe
    -1.49
     största
    -1.49
     föres
    -1.49
    featureID
    -1.48
     メニュー
    -1.47
    POSITIVE LOGITS
     but
    1.55
     significativa
    1.43
    </b>
    1.41
    財布
    1.38
    <h2>
    1.36
    Such
    1.35
    ้งาน
    1.34
    All
    1.33
     mostrando
    1.32
     ExecuteAsync
    1.32
    Activations Density 0.001%

    No Known Activations