© 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. 22-GEMMASCOPE-RES-131K
    4. 36402
    Prev
    Next
    INDEX
    Explanations

    file positions and code

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

    The neuron fires on standalone numeric tokens (e.g. line numbers, versions, diffs) in code or logs.

    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
     praia
    -1.11
     vagas
    -1.06
     páss
    -1.05
    に入り
    -1.05
     intelig
    -1.05
     müzik
    -1.05
     gavetas
    -1.05
     paño
    -1.02
     vín
    -1.02
     pão
    -1.00
    POSITIVE LOGITS
     of
    1.30
    	
    1.00
     تعريف
    0.92
     Université
    0.91
     out
    0.91
    }\
    0.90
     soportes
    0.89
     телефону
    0.88
    ."
    0.88
    ot
    0.88
    Activations Density 0.002%

    No Known Activations