© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28102
    Prev
    Next
    INDEX
    Explanations

    license terms and conditions

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

    The neuron fires on standalone numeric tokens (e.g. line numbers, version or year numbers) in code/comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -1.22
     <",
    -1.21
     importants
    -1.18
     aſ
    -1.17
     absolue
    -1.16
     aussit
    -1.16
     correcte
    -1.15
    ጺ
    -1.15
     INDONESIA
    -1.15
     türkiye
    -1.13
    POSITIVE LOGITS
     Also
    1.18
     speziell
    1.09
     zuerst
    1.09
     speziellen
    1.02
     Other
    1.02
     mientras
    1.00
     nörd
    0.97
     DoD
    0.96
     Specifically
    0.95
     mehrere
    0.94
    Activations Density 0.001%

    No Known Activations