© 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. 74671
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty or observation

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

    the use of emphatic adverbs or discourse markers (like “typically,” “apparently,” “clearly,” “obviously”) that signal certainty or emphasis in statements.

    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
     not
    -2.16
    "]));
    -1.89
     to
    -1.79
                     
    -1.77
                   
    -1.75
     
    -1.72
                      
    -1.72
       
    -1.70
     more
    -1.70
         
    -1.63
    POSITIVE LOGITS
     there
    2.78
     it
    2.72
     you
    2.45
     we
    2.19
     your
    2.02
     they
    1.95
    ougars
    1.82
    橚
    1.71
    　　*
    1.68
    跣
    1.63
    Activations Density 0.070%

    No Known Activations