© 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. 70787
    Prev
    Next
    INDEX
    Explanations

    php file or address

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

    The neuron fires on numeric tokens (digits and multi‐digit numbers) in code or text, i.e. it detects numbers in programming contexts.

    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
     its
    -1.12
    消化
    -1.01
    翻攝
    -1.00
    十八
    -0.99
    一八
    -0.99
    国防
    -0.96
    annon
    -0.94
    ян
    -0.90
     Konkur
    -0.90
     phenomenal
    -0.89
    POSITIVE LOGITS
    素敵
    1.07
     contou
    1.02
    あっという
    0.98
    ícia
    0.97
    !!!!!!!
    0.96
     agregó
    0.96
    !!!!!!
    0.94
    今度
    0.94
     итоге
    0.92
    素敵な
    0.91
    Activations Density 0.043%

    No Known Activations