© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119380
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

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

    The neuron activates on capitalized or all‐caps tokens—that is, proper names, acronyms, and similar named entities.

    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
    </sup>
    -3.27
     Any
    -2.39
     Anyone
    -2.38
     industrious
    -2.20
    慕容
    -2.19
    齜
    -2.17
     malady
    -2.17
     artinya
    -2.16
    劉
    -2.16
     Anybody
    -2.14
    POSITIVE LOGITS
    ’
    3.45
     andere
    3.22
    ruguay
    2.84
     WHICH
    2.72
    
    2.70
     \
    2.59
     melap
    2.58
     outras
    2.53
    儅
    2.50
    
    2.50
    Activations Density 0.239%

    No Known Activations