© 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. 1851
    Prev
    Next
    INDEX
    Explanations

    introducing additional information

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

    The neuron fires on the discourse adverb “additionally.”

    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
    *
    -1.74
     from
    -1.64
     selanjutnya
    -1.54
    いぐるみ
    -1.53
     Because
    -1.52
    *}[
    -1.51
    to
    -1.46
     großes
    -1.45
     pasangan
    -1.44
     menengah
    -1.44
    POSITIVE LOGITS
     \&
    2.05
    Dengan
    1.86
    焄
    1.77
    轵
    1.77
    
    1.72
     roligt
    1.70
    ános
    1.70
    Setiap
    1.67
     aktiviteter
    1.66
    嵎
    1.66
    Activations Density 0.045%

    No Known Activations