© 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. 22-GEMMASCOPE-RES-131K
    7. 71483
    Prev
    Next
    INDEX
    Explanations

    certainly and definitely

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

    The neuron is primarily detecting emphatic adverbs or degree modifiers (e.g. definitely, certainly) that heighten or stress a statement.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     actually
    -1.27
     basically
    -1.23
    訇
    -1.20
    実は
    -1.20
     Basically
    -1.19
     essentially
    -1.17
     magari
    -1.16
    其實
    -1.15
    どうしても
    -1.14
     even
    -1.13
    POSITIVE LOGITS
     more
    1.19
    ousse
    1.05
     definitivamente
    1.04
     anyone
    1.02
     meglio
    0.99
     lebih
    0.97
     there
    0.96
     among
    0.95
     any
    0.94
     более
    0.94
    Activations Density 0.033%

    No Known Activations