© 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. 10896
    Prev
    Next
    INDEX
    Explanations

    lots of

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

    This neuron detects emphatic quantity phrases—especially “lots of” (and its variants) indicating large amounts.

    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
     gewi
    -2.11
     zoude
    -2.02
    雠
    -1.99
     utilizados
    -1.97
    ophageal
    -1.93
    搋
    -1.92
    肏
    -1.91
    
    -1.91
     ujedno
    -1.90
     bedankt
    -1.88
    POSITIVE LOGITS
     Adding
    2.30
     unwavering
    2.05
     Creating
    2.05
     Depending
    2.00
     If
    2.00
     Having
    1.98
    كتشاف
    1.98
     ....
    1.98
     Both
    1.96
     quaint
    1.96
    Activations Density 0.013%

    No Known Activations