© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118924
    Prev
    Next
    INDEX
    Explanations

    null value placeholder

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

    The neuron activates on the literal “null” token.

    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
    ほんと
    -2.63
    谖
    -2.59
    あー
    -2.56
     bizarre
    -2.48
    ーーーー
    -2.45
    さぁ
    -2.44
    あぁ
    -2.44
    めちゃくちゃ
    -2.44
    さあ
    -2.41
    凄く
    -2.41
    POSITIVE LOGITS
    柽
    2.59
    ку
    2.42
    镦
    2.41
    玏
    2.39
    ൎ
    2.39
    т
    2.34
    眛
    2.25
    
    2.23
    軔
    2.19
    🛇
    2.16
    Activations Density 0.012%

    No Known Activations