© 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. 34-GEMMASCOPE-RES-131K
    7. 102618
    Prev
    Next
    INDEX
    Explanations

    at your option

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

    The neuron flags formal boilerplate phrases in which a discretionary choice or legal/licensing terms are stated (e.g. “selected based on…,” “at your option,” “either version…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     卒業
    -0.77
    Defines
    -0.77
     gobernador
    -0.76
     Dessert
    -0.74
    EXPECTED
    -0.73
    UnsafeEnabled
    -0.73
    コチラ
    -0.72
     AppColors
    -0.72
    ・・。
    -0.71
    ことが多い
    -0.71
    POSITIVE LOGITS
     discretion
    2.64
     sole
    2.06
    sole
    1.49
     at
    1.47
     discretionary
    1.42
     Discretion
    1.33
    cretion
    1.16
     absolute
    1.15
    Sole
    1.13
     decide
    1.05
    Activations Density 0.033%

    No Known Activations