© 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. 85483
    Prev
    Next
    INDEX
    Explanations

    exceedingly difficult/good/popular

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

    The neuron specializes in spotting intense descriptive modifiers—especially high-strength adjectives and adverbs (e.g. exceedingly, tirelessly, sublime) that signal extremity or emphasis.

    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
    '
    -4.47
     The
    -3.44
    2
    -3.28
    5
    -3.17
    0
    -3.16
    6
    -3.16
    4
    -3.11
    7
    -3.08
    3
    -2.92
    ates
    -2.80
    POSITIVE LOGITS
    襤
    2.56
     groter
    2.53
    骓
    2.42
    蔸
    2.34
    砣
    2.34
    繻
    2.34
     mohli
    2.31
    罴
    2.28
    鬩
    2.28
    
    2.27
    Activations Density 0.007%

    No Known Activations