© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58638
    Prev
    Next
    INDEX
    Explanations

    most and more followed by adjectives

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

    The neuron flags degree modifiers—especially “more” and “most”—i.e., comparative/superlative intensifier words.

    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
     
    -1.46
     также
    -1.43
    ↵
    -1.43
     We
    -1.39
    by
    -1.38
     également
    -1.38
     but
    -1.38
     -
    -1.37
    但也
    -1.37
    k
    -1.34
    POSITIVE LOGITS
     controllare
    1.66
    กล้
    1.64
    虓
    1.62
    providedIn
    1.61
    焢
    1.57
    ௡
    1.55
    飧
    1.54
    
    1.53
    珅
    1.50
    ⢌
    1.50
    Activations Density 0.017%

    No Known Activations